© 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. 41052
    Prev
    Next
    INDEX
    Explanations

    website urls and code

    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
     sequence
    -0.29
    enc
    -0.29
    crate
    -0.28
    åºı
    -0.27
     Sequence
    -0.27
    ä¹İ
    -0.26
    esty
    -0.26
    åºıåĪĹ
    -0.26
     aperture
    -0.26
     sequences
    -0.25
    POSITIVE LOGITS
    ÃŃd
    0.28
    TION
    0.28
    Rad
    0.26
    ância
    0.26
    itung
    0.26
    quina
    0.26
     Rad
    0.25
    .keep
    0.25
    -trade
    0.25
    åı¸
    0.24
    Activations Density 0.000%

    No Known Activations