© 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. 25620
    Prev
    Next
    INDEX
    Explanations

    document beginnings

    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
    æĹ©æĹ¥
    -0.26
    metic
    -0.26
     taxation
    -0.25
    å¾Īå¿«
    -0.25
    -mf
    -0.25
    timer
    -0.25
    åıªæĢķ
    -0.25
    sic
    -0.25
    è¾ĥå¿«
    -0.25
    uenta
    -0.24
    POSITIVE LOGITS
    ä¸ĢåłĨ
    0.26
    olars
    0.26
     Closing
    0.24
    orting
    0.24
    æĺ¾
    0.24
    LI
    0.24
    åħļç»Ħç»ĩ
    0.23
    åħ¨
    0.23
    è²·ãģĦ
    0.23
    被æīĵ
    0.23
    Activations Density 0.024%

    No Known Activations