© 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. 108499
    Prev
    Next
    INDEX
    Explanations

    minus sign

    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
    erate
    -0.32
    casting
    -0.27
    capture
    -0.26
    stract
    -0.26
    oe
    -0.25
    output
    -0.25
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.25
    åľ¨äºİ
    -0.25
     ká»ĭch
    -0.24
    CASE
    -0.24
    POSITIVE LOGITS
    åij¨å¹´
    0.32
     dispos
    0.27
     realities
    0.25
     autom
    0.25
    ä»ĺãģį
    0.25
    æĹ¥èµ·
    0.25
    å·¦åı³
    0.24
    Ñģла
    0.24
     redund
    0.24
    -paid
    0.24
    Activations Density 1.149%

    No Known Activations