© 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. 43841
    Prev
    Next
    INDEX
    Explanations

    Code/programming comments

    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
    ptive
    -0.31
     heats
    -0.28
    morph
    -0.28
     morph
    -0.27
    渥
    -0.27
    Uvs
    -0.26
     Feinstein
    -0.26
    andle
    -0.25
    éĢĥéģ¿
    -0.25
    prot
    -0.25
    POSITIVE LOGITS
    ela
    0.29
    å¥ī
    0.26
    æľªç»ı
    0.25
    imenti
    0.25
    ег
    0.25
    ib
    0.25
    ebb
    0.24
     ch
    0.24
     Ch
    0.24
     kernel
    0.24
    Activations Density 0.001%

    No Known Activations