Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2763
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    顶部
    -0.08
    ically
    -0.07
    iento
    -0.07
     confirmPassword
    -0.07
    尽力
    -0.07
    扦
    -0.07
     holding
    -0.07
    джер
    -0.07
     dissent
    -0.07
     amt
    -0.06
    POSITIVE LOGITS
    ]|[
    0.07
    _PF
    0.06
     eget
    0.06
     ellipse
    0.06
     Cartesian
    0.06
    рог
    0.06
     hes
    0.06
    {EIF
    0.06
     Açık
    0.06
     Chicago
    0.06
    Activations Density 0.006%

    No Known Activations