© 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. 35-TRANSCODER-HP
    7. 39359
    Prev
    Next
    INDEX
    Explanations

    documents containing unusual characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įå®Į
    -0.29
    WK
    -0.28
    HK
    -0.27
     utilize
    -0.26
    KW
    -0.26
    çļĦåħ³æ³¨
    -0.26
    NK
    -0.26
     McKay
    -0.26
    ellant
    -0.25
    hk
    -0.25
    POSITIVE LOGITS
     fis
    0.30
     ifs
    0.28
     fsm
    0.27
    is
    0.26
    each
    0.26
     orth
    0.26
     cres
    0.25
     twó
    0.25
    thes
    0.25
     Tomas
    0.25
    Activations Density 0.026%

    No Known Activations