© 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. 12-TRANSCODER-HP
    7. 24109
    Prev
    Next
    INDEX
    Explanations

    drinks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Norris
    -0.26
     tamp
    -0.26
     uden
    -0.25
    åľ¨çº¿
    -0.25
     licens
    -0.25
    客æĪ·éľĢæ±Ĥ
    -0.24
    ObjectContext
    -0.24
     ObjectOutputStream
    -0.24
    åĪĽä½ľ
    -0.24
    -court
    -0.24
    POSITIVE LOGITS
    ago
    0.30
    gué
    0.28
     understanding
    0.28
    æ¯Ĵ
    0.28
    AGO
    0.27
     Exp
    0.26
    inke
    0.25
    .Views
    0.25
     Cruise
    0.24
    ande
    0.24
    Activations Density 0.007%

    No Known Activations