© 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. 149308
    Prev
    Next
    INDEX
    Explanations

    Legal documents and outdated articles

    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
     realise
    -0.27
    ÈĻ
    -0.27
    æŧ
    -0.26
    Foreign
    -0.26
     realised
    -0.26
     Communities
    -0.26
    /right
    -0.26
    Expired
    -0.25
    akov
    -0.25
     remind
    -0.25
    POSITIVE LOGITS
    ức
    0.29
    ede
    0.29
    æĹ¥èµ·
    0.28
     resistance
    0.27
    eday
    0.27
    uf
    0.26
    ä¸Ģå¤ľ
    0.25
    éĺ»åĬĽ
    0.25
    elige
    0.25
    åĨ¶
    0.25
    Activations Density 0.063%

    No Known Activations