© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43904
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    ottle
    -0.28
     Fired
    -0.27
     tweeting
    -0.27
     authorised
    -0.26
    logue
    -0.26
     Authorized
    -0.26
    Tiles
    -0.25
    ECH
    -0.25
    licative
    -0.25
    /cop
    -0.25
    POSITIVE LOGITS
    7
    0.35
    3
    0.32
    5
    0.31
    es
    0.31
    9
    0.30
    -
    0.30
    2
    0.30
     &=
    0.29
    8
    0.28
     times
    0.28
    Activations Density 0.049%

    No Known Activations