© 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. 30319
    Prev
    Next
    INDEX
    Explanations

    avin

    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
    Negative Logits
    èĭĹ
    -0.32
    pu
    -0.31
    PU
    -0.29
    cz
    -0.27
     PU
    -0.25
    men
    -0.24
    Reporting
    -0.24
    å¾®å¦Ļ
    -0.24
    注
    -0.23
     exact
    -0.23
    POSITIVE LOGITS
    åĮĹæĸ¹
    0.28
    åľ¨è¿Ļæĸ¹éĿ¢
    0.27
    AME
    0.25
    roys
    0.25
     unins
    0.24
    OLUTE
    0.24
    sweet
    0.24
    dsa
    0.24
    _tcb
    0.24
    çĪ°
    0.24
    Activations Density 5.616%

    No Known Activations