© 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. 41330
    Prev
    Next
    INDEX
    Explanations

    c

    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
    controlled
    -0.29
     controlled
    -0.29
    -controlled
    -0.28
     sw
    -0.26
    è¾Ĭ
    -0.26
    -transfer
    -0.26
    ìħĢ
    -0.25
     cu
    -0.25
    oken
    -0.25
    _peer
    -0.25
    POSITIVE LOGITS
    ich
    0.29
    _/
    0.28
    æѦ
    0.26
    vÃŃ
    0.26
    ToDelete
    0.26
    mour
    0.25
    icho
    0.25
    THREAD
    0.25
    quals
    0.25
    æıIJéĢŁ
    0.25
    Activations Density 0.002%

    No Known Activations