© 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. 9-TRANSCODER-HP
    7. 30171
    Prev
    Next
    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ball
    -0.27
    ivate
    -0.26
    quire
    -0.26
    than
    -0.25
     Vaccine
    -0.25
    åĸĥ
    -0.25
    å¡ijèĥ¶
    -0.25
    acie
    -0.25
    å¸ĤåľºéľĢæ±Ĥ
    -0.25
    çĻ½è¡£
    -0.24
    POSITIVE LOGITS
    пеÑĩ
    0.28
    ellas
    0.27
     Mex
    0.25
    {}]
    0.24
    entlich
    0.24
    æĹĭ
    0.24
    passwd
    0.24
    人å¿ĥ
    0.23
     bund
    0.23
    Forgot
    0.23
    Activations Density 13.706%

    No Known Activations