© 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. 41082
    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
    spo
    -0.28
    asta
    -0.27
    oping
    -0.26
    åĪ·
    -0.26
    .SQL
    -0.26
    á»Ļc
    -0.25
     renew
    -0.25
    ulu
    -0.24
    å¿ĥçIJĨ
    -0.24
    guns
    -0.24
    POSITIVE LOGITS
    isclosed
    0.27
     Pc
    0.27
    itchens
    0.27
    æŶè£ħ
    0.25
    mits
    0.25
    çĪµå£«
    0.25
    alse
    0.25
    IÃĬ
    0.25
    merce
    0.24
    ormap
    0.23
    Activations Density 0.001%

    No Known Activations