© 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. 24-TRANSCODER-HP
    7. 149375
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ("{
    -0.32
    ('{
    -0.24
     sophistication
    -0.24
     affair
    -0.24
    PostExecute
    -0.23
    move
    -0.23
    etat
    -0.23
    ä¸ĢæŃ¥
    -0.23
    _REGS
    -0.23
     влад
    -0.23
    POSITIVE LOGITS
    iele
    0.31
    ches
    0.29
    eland
    0.29
     truly
    0.29
    acies
    0.28
     able
    0.28
     callable
    0.28
    åĦĢ
    0.28
     compatible
    0.28
     meaningful
    0.27
    Activations Density 0.903%

    No Known Activations