© 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. 149133
    Prev
    Next
    INDEX
    Explanations

    social

    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
    alto
    -0.29
    aire
    -0.28
    rs
    -0.26
    æŁĶæĢ§
    -0.26
    s
    -0.26
     associative
    -0.25
    æķ´çIJĨ
    -0.25
    éĽĨ
    -0.25
    建ç«ĭ
    -0.24
    建ç«ĭäºĨ
    -0.24
    POSITIVE LOGITS
    éĢ¢
    0.28
    ester
    0.28
    ä¼Ĺ人
    0.27
    èĩĤ
    0.27
    碧
    0.27
    ä¼Ĺ
    0.26
     Roller
    0.25
    æĺµ
    0.25
     roller
    0.25
    IRD
    0.25
    Activations Density 0.017%

    No Known Activations