© 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. 43631
    Prev
    Next
    INDEX
    Explanations

    cell

    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
    次
    -0.33
    çIJĨ
    -0.30
    ypy
    -0.28
    鼨
    -0.28
     weighs
    -0.28
     weights
    -0.26
     rain
    -0.26
    è¿ŀäºij
    -0.25
     weight
    -0.25
    .weight
    -0.25
    POSITIVE LOGITS
     cell
    0.47
    cell
    0.40
     Cell
    0.39
    ç»Ĩèĥŀ
    0.39
    Cell
    0.38
    (cell
    0.38
    CELL
    0.35
     CELL
    0.34
    	cell
    0.33
    _cell
    0.33
    Activations Density 0.004%

    No Known Activations