© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108972
    Prev
    Next
    INDEX
    Explanations

    sub

    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
    Not in Any Lists

    No Comments

    Negative Logits
     aras
    -0.28
    grund
    -0.27
    ç¡Ģ
    -0.26
    é¢ĸ
    -0.26
    Hands
    -0.25
    èĤ¿
    -0.24
    gründe
    -0.24
    POOL
    -0.24
    éĺ²ç©º
    -0.23
     Regents
    -0.23
    POSITIVE LOGITS
    rito
    0.33
    ä¹IJéĺŁ
    0.28
    รà¸ĵ
    0.27
    asting
    0.27
     ric
    0.26
    onation
    0.26
    åŃ£åIJİ
    0.25
    åįĹæĸ¹
    0.25
    履约
    0.25
    æĥ³å¿µ
    0.24
    Activations Density 0.895%

    No Known Activations