© 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. 32-TRANSCODER-HP
    7. 43351
    Prev
    Next
    INDEX
    Explanations

    off

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omanip
    -0.27
    个åĪ«
    -0.27
     pré
    -0.27
    代
    -0.26
    æİĮ
    -0.26
    pre
    -0.26
    è¦Ĩ
    -0.26
    éĻį
    -0.26
     pres
    -0.25
    tingham
    -0.25
    POSITIVE LOGITS
     off
    0.93
    off
    0.84
     Off
    0.80
    -off
    0.75
    Off
    0.75
    (off
    0.69
    _off
    0.69
     OFF
    0.68
    offs
    0.67
    OFF
    0.66
    Activations Density 0.001%

    No Known Activations