© 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. 24007
    Prev
    Next
    INDEX
    Explanations

    time

    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
    LogLevel
    -0.28
    称ä¹ĭ
    -0.27
    yms
    -0.25
    åľ¨è·¯ä¸Ĭ
    -0.25
    Known
    -0.25
    åIJİåĭ¤
    -0.25
    fly
    -0.25
    _known
    -0.25
    really
    -0.25
    -under
    -0.25
    POSITIVE LOGITS
    lymp
    0.24
     Tune
    0.24
     bis
    0.24
    MRI
    0.24
    åĪĨå±Ģ
    0.23
     оÑĢганизаÑĨиÑı
    0.23
    æĹ¥æĬ¥è®°èĢħ
    0.23
    ansson
    0.23
    åĪĪ
    0.23
    iect
    0.23
    Activations Density 0.002%

    No Known Activations