© 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. 43636
    Prev
    Next
    INDEX
    Explanations

    Ch

    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
     Dud
    -0.27
    .INSTANCE
    -0.26
     Ill
    -0.25
    chers
    -0.25
    è§Ģå¯Ł
    -0.25
    ORB
    -0.25
    lds
    -0.24
     innoc
    -0.24
    è§Ĥå¯Ł
    -0.24
    Observ
    -0.24
    POSITIVE LOGITS
    å¥Ĺ
    0.28
    iard
    0.28
    opause
    0.26
    ç©´
    0.25
     drum
    0.25
    APE
    0.25
    åİĭ
    0.24
    amber
    0.24
    Tar
    0.24
    DRAW
    0.24
    Activations Density 0.001%

    No Known Activations