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. 24537
    Prev
    Next
    INDEX
    Explanations

    say "}"

    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
    ができ
    -0.08
    méd
    -0.07
     chociaż
    -0.07
     �
    -0.07
     Sept
    -0.07
     Automotive
    -0.07
    				↵				↵
    -0.07
     Алексан
    -0.07
    illaume
    -0.07
     Fußball
    -0.06
    POSITIVE LOGITS
    从严
    0.07
    Ւ
    0.07
    Presentation
    0.07
     regardless
    0.07
    acked
    0.06
    .returnValue
    0.06
    toLowerCase
    0.06
     trace
    0.06
     tally
    0.06
    ńst
    0.06
    Activations Density 0.018%

    No Known Activations