© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 40989
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    Negative Logits
    yers
    -0.35
    rts
    -0.29
    irs
    -0.28
    峡
    -0.27
    IRT
    -0.25
    rais
    -0.25
    yer
    -0.25
    ye
    -0.25
     ent
    -0.25
    urs
    -0.25
    POSITIVE LOGITS
    wy
    0.33
    ely
    0.29
    ete
    0.29
    pointer
    0.28
    ety
    0.28
    åħŃ个
    0.28
    oly
    0.28
    ick
    0.28
    ónico
    0.27
    iam
    0.26
    Activations Density 0.000%

    No Known Activations