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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 14126
    Prev
    Next
    INDEX
    Explanations

    trek

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cand
    -0.07
    阊
    -0.07
     dau
    -0.07
     august
    -0.06
    ului
    -0.06
    -clock
    -0.06
    ساس
    -0.06
     and
    -0.06
    awns
    -0.06
    áng
    -0.06
    POSITIVE LOGITS
    "){
    ↵
    0.08
    Represent
    0.08
    ']));↵
    0.07
    娑
    0.07
    📱
    0.07
    具有一定
    0.07
    实地
    0.07
    ");
    ↵
    0.07
    一枚
    0.07
    χ
    0.07
    Activations Density 0.002%

    No Known Activations