© 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. 25-TRANSCODER-HP
    7. 109513
    Prev
    Next
    INDEX
    Explanations

    Research articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¿Ļå¥Ĺ
    -0.28
    ä¸ĢåįĬ
    -0.26
    åħ´èĩ´
    -0.26
    侯
    -0.25
    spiel
    -0.25
    å¥Ĺ
    -0.25
    ä¸ĢåľĪ
    -0.25
    >`↵
    -0.25
    å½ĵçĦ¶
    -0.25
    ä¸Ģå¥Ĺ
    -0.25
    POSITIVE LOGITS
    _methods
    0.26
    igans
    0.26
    ynchronously
    0.26
    OnUiThread
    0.25
    veys
    0.25
     increasing
    0.25
    亿ä¸ĩ
    0.24
    (using
    0.24
    :animated
    0.24
    è¦ģæĬĬ
    0.24
    Activations Density 0.988%

    No Known Activations