© 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. 24-TRANSCODER-HP
    7. 151388
    Prev
    Next
    INDEX
    Explanations

    formal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¶Ĭ大
    -0.27
    æł½
    -0.27
    尾巴
    -0.27
     rode
    -0.26
    Occurred
    -0.25
    Craft
    -0.25
     Exiting
    -0.25
     craft
    -0.25
    缮çļĦæĺ¯
    -0.24
     licensing
    -0.24
    POSITIVE LOGITS
     Griffith
    0.29
    ç§ĺ书
    0.26
    hero
    0.26
    |i
    0.26
    uniform
    0.26
    hom
    0.25
    xf
    0.24
    zers
    0.24
     Cent
    0.24
     centres
    0.24
    Activations Density 0.124%

    No Known Activations