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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    11. 8635
    Prev
    Next
    INDEX
    Explanations

    understand

    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
    稍微
    -0.07
    此时
    -0.07
     successful
    -0.07
    inux
    -0.07
    jącym
    -0.07
    엜
    -0.07
    ilty
    -0.06
    isper
    -0.06
     Stainless
    -0.06
    .contentView
    -0.06
    POSITIVE LOGITS
    菲律宾
    0.07
    -import
    0.07
    desc
    0.07
    霉素
    0.07
    け
    0.06
    .*?)
    0.06
    (PORT
    0.06
    .hstack
    0.06
    ศาส
    0.06
    ABLE
    0.06
    Activations Density 0.017%

    No Known Activations