© 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. 108802
    Prev
    Next
    INDEX
    Explanations

    in

    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
    æĹłéĻIJ
    -0.29
    nze
    -0.28
    åĿIJä¸ĭ
    -0.27
    æ´»ä¸ĭåİ»
    -0.26
    itation
    -0.26
    lok
    -0.26
    åĭĥåĭĥ
    -0.26
    çĻ½è¡£
    -0.25
    åIJİèĢħ
    -0.25
    alion
    -0.25
    POSITIVE LOGITS
    .shtml
    0.31
    è¿Ļç§įæĸ¹å¼ı
    0.30
    Contr
    0.27
     sóc
    0.25
     reality
    0.25
    .leading
    0.24
    éļĽ
    0.24
    .wrap
    0.24
     way
    0.24
     Contrast
    0.24
    Activations Density 2.104%

    No Known Activations