© 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. 109538
    Prev
    Next
    INDEX
    Explanations

    king

    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
    èī¯å¿ĥ
    -0.28
    ç§į
    -0.27
    éĹ´éļĶ
    -0.27
    çİĩ
    -0.25
    .norm
    -0.25
    çĻ½
    -0.25
    è·¯ä¸Ĭ
    -0.25
    èĩªå·±åĸľæ¬¢
    -0.25
    æĸ¹
    -0.24
    mö
    -0.24
    POSITIVE LOGITS
    åĺı
    0.27
    群ä½ĵ
    0.25
     ResourceManager
    0.25
    dict
    0.25
    _lift
    0.24
    loth
    0.24
     ãĢIJ
    0.24
    too
    0.23
    åijĬè¯ī大家
    0.23
    like
    0.23
    Activations Density 0.130%

    No Known Activations