© 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. 40265
    Prev
    Next
    INDEX
    Explanations

    of

    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
    API
    -0.31
    BC
    -0.30
    avi
    -0.29
    math
    -0.29
    CD
    -0.28
    CM
    -0.28
    PC
    -0.28
    CB
    -0.28
    IR
    -0.28
    PP
    -0.28
    POSITIVE LOGITS
     The
    0.39
     the
    0.39
    nThe
    0.32
     tph
    0.30
     Humanity
    0.30
     THE
    0.30
    ,the
    0.30
     Tmin
    0.29
    	the
    0.29
    'gc
    0.29
    Activations Density 24.599%

    No Known Activations