© 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. 109079
    Prev
    Next
    INDEX
    Explanations

    study

    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
    obao
    -0.27
    tings
    -0.26
     Rating
    -0.25
    åī¥
    -0.24
    itech
    -0.24
    ocular
    -0.24
    éĩįè§Ĩ
    -0.24
    ä¸ĭ车
    -0.24
    soon
    -0.24
    æī¯
    -0.24
    POSITIVE LOGITS
    åľ°éģĵ
    0.27
    usto
    0.26
     OMIT
    0.25
    çĶ¨æ°´
    0.25
    åĽ½ç±į
    0.25
     around
    0.25
    ä¸Ĭä¸ĭ游
    0.24
    rior
    0.24
    çŃĸçķ¥
    0.24
    å¿ħä¸įåı¯å°ij
    0.24
    Activations Density 0.900%

    No Known Activations