© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 52289
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    Spots quoted string literals (text inside quotation marks), especially in JSON/code-like contexts.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exe
    -0.08
    也希望
    -0.08
     FITNESS
    -0.08
    .minLength
    -0.08
    近两年
    -0.08
    /jpeg
    -0.08
     xls
    -0.07
     xe
    -0.07
     Offering
    -0.07
    @(
    -0.07
    POSITIVE LOGITS
    "
    0.07
    죕
    0.07
    ать
    0.07
    ，“
    0.07
     Ballard
    0.07
    꾈
    0.07
    wall
    0.07
     Bale
    0.07
     Williamson
    0.07
    agher
    0.07
    Activations Density 0.035%

    No Known Activations