© 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. 11-RESID-POST-AA
    11. 110005
    Prev
    Next
    INDEX
    Explanations

    Nathan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gale
    -0.08
     stages
    -0.08
    .isLoading
    -0.07
     MemoryStream
    -0.07
    .jsx
    -0.07
     Dü
    -0.07
    layers
    -0.07
    那种
    -0.07
    邮轮
    -0.07
    _samples
    -0.06
    POSITIVE LOGITS
    “If
    0.08
     hyper
    0.08
    ทา
    0.08
    她说
    0.08
     appropriated
    0.07
     Ibid
    0.07
    电子邮件
    0.07
     Metropolitan
    0.07
    平均每
    0.07
    钚
    0.07
    Activations Density 0.026%

    No Known Activations