© 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. 23-TRANSCODER-HP
    7. 23383
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    (dead
    -0.26
     Mort
    -0.26
    ogle
    -0.26
     Shoulder
    -0.25
     transc
    -0.25
    åij¨è½¬
    -0.25
     stopping
    -0.25
     stop
    -0.25
     hopefully
    -0.24
    quires
    -0.24
    POSITIVE LOGITS
    bi
    0.28
    åľ°è²Į
    0.28
    赤
    0.28
    bler
    0.27
    Facade
    0.27
    FUL
    0.26
    mise
    0.25
    _STAR
    0.25
    STAR
    0.24
    iant
    0.24
    Activations Density 0.003%

    No Known Activations