© 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. 108051
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
    æĸĹäºī
    -0.29
    åľ¨åºĬä¸Ĭ
    -0.28
    bery
    -0.26
    \Lib
    -0.25
     Derm
    -0.25
    举
    -0.25
    æ³µ
    -0.24
    æĬķæľº
    -0.24
    ç©ij
    -0.24
    è¿ŀæİ¥
    -0.24
    POSITIVE LOGITS
    访è°Ī
    0.30
    enden
    0.29
     interviewed
    0.29
    è§Ĥå¯Ł
    0.29
    å®ŀåľ°
    0.29
    éĻĽ
    0.27
    主è§Ĥ
    0.27
    éĹ®åį·
    0.27
     questionnaire
    0.27
     interviewing
    0.26
    Activations Density 0.910%

    No Known Activations