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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53772
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consumers
    -0.28
    人大代表
    -0.27
     customers
    -0.27
    åĢºæĿĥ人
    -0.27
    æ°ijå¿ĥ
    -0.26
    æĹıèĩªæ²»å·ŀ
    -0.26
    ç»ıéĶĢåķĨ
    -0.26
    åѦåŃIJ
    -0.26
    åĬĽè¿ĺæĺ¯
    -0.26
    [child
    -0.26
    POSITIVE LOGITS
     Role
    0.30
    -role
    0.29
    Role
    0.28
     role
    0.27
    ongs
    0.27
    ãĥĩãĤ£
    0.26
    é¡¿
    0.26
    éĤ¦
    0.25
    urger
    0.25
    role
    0.24
    Activations Density 0.010%

    No Known Activations