© 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
    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. 20773
    Prev
    Next
    INDEX
    Explanations

    second language

    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
     Neck
    -0.07
     Advocate
    -0.07
    .^
    -0.07
     Pittsburgh
    -0.07
     nerv
    -0.06
     Cuban
    -0.06
    ступ
    -0.06
     inputValue
    -0.06
    .tv
    -0.06
    벤
    -0.06
    POSITIVE LOGITS
     bounty
    0.07
     güc
    0.07
    ambah
    0.07
     требуется
    0.07
    详解
    0.07
    がかか
    0.07
    о
    0.07
    ᒌ
    0.06
    قال
    0.06
    홀
    0.06
    Activations Density 0.010%

    No Known Activations