© 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. 43122
    Prev
    Next
    INDEX
    Explanations

    medicine/bodily functions

    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
     charge
    -0.34
     Charge
    -0.32
    iges
    -0.28
    满
    -0.28
    charges
    -0.28
    被æīĵ
    -0.27
    voy
    -0.26
    лÑĮн
    -0.26
     tic
    -0.26
    Charge
    -0.26
    POSITIVE LOGITS
     Ir
    0.27
    Ir
    0.27
     Thr
    0.27
    çŃ¹
    0.26
    èĻļæŀĦ
    0.26
    ksam
    0.25
     ir
    0.25
    åIJ¦
    0.24
     randomized
    0.24
    rc
    0.24
    Activations Density 0.000%

    No Known Activations