© 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. 108893
    Prev
    Next
    INDEX
    Explanations

    location and time

    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
    éªĹ
    -0.28
    容å¿į
    -0.26
    éģİç¨ĭä¸Ń
    -0.26
     refl
    -0.25
     eviction
    -0.25
    intel
    -0.24
     chances
    -0.24
    Nhap
    -0.23
     allowances
    -0.23
    ãģ®ä¸Ģ
    -0.23
    POSITIVE LOGITS
    æ´¾åĩº
    0.28
     Feder
    0.28
     certified
    0.27
    lagen
    0.27
    éļ¾å¾Ĺ
    0.26
    ilm
    0.25
    ÑĥÑĩа
    0.25
    è¿ĩæĿ¥
    0.24
     Masc
    0.24
     behold
    0.24
    Activations Density 1.014%

    No Known Activations