© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 110519
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sigue
    -0.07
     matchup
    -0.07
    不确定性
    -0.07
     rico
    -0.07
    Ult
    -0.07
    僚
    -0.07
    突破
    -0.07
     navigating
    -0.07
    看你
    -0.06
    Allocate
    -0.06
    POSITIVE LOGITS
    Tony
    0.08
     площад
    0.07
    :inline
    0.06
    🇿
    0.06
    맹
    0.06
    主权
    0.06
    Industry
    0.06
     Sidney
    0.06
     nome
    0.06
    좁
    0.06
    Activations Density 0.047%

    No Known Activations