© 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. 30-TRANSCODER-HP
    7. 94911
    Prev
    Next
    INDEX
    Explanations

    First

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    InProgress
    -0.27
    isson
    -0.27
     Prosper
    -0.26
    éĤ
    -0.26
     financially
    -0.25
    ycz
    -0.25
    èľĤ
    -0.25
    sector
    -0.24
    rente
    -0.24
    -parser
    -0.24
    POSITIVE LOGITS
    å¦Ī
    0.27
    æł¡
    0.26
    lug
    0.26
    个å¤ļ
    0.25
    æ±°
    0.25
    amp
    0.25
    bob
    0.25
     géné
    0.24
    çŃ·
    0.24
     glob
    0.24
    Activations Density 0.004%

    No Known Activations