© 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. 108953
    Prev
    Next
    INDEX
    Explanations

    no

    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
    åľ¨å¤ĸ
    -0.28
    beck
    -0.26
    ãģ¾ãģĻ
    -0.25
    é£ĺ
    -0.25
    rhs
    -0.25
    shared
    -0.24
     rá
    -0.24
    rement
    -0.23
    çļĦå°±æĺ¯
    -0.23
    rove
    -0.23
    POSITIVE LOGITS
    æĿĨèıĮ
    0.29
    ä»Ģä¹ĪæŶåĢĻ
    0.27
    usu
    0.27
    åĽ½ç±į
    0.27
    issen
    0.26
     instead
    0.26
    eff
    0.26
     phúc
    0.26
     Slash
    0.26
    acus
    0.25
    Activations Density 0.372%

    No Known Activations