© 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. 109063
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    æĪĸèĢħåħ¶ä»ĸ
    -0.29
     dereg
    -0.27
    asca
    -0.27
     redevelopment
    -0.26
     OST
    -0.26
    å¤ļç§įå½¢å¼ı
    -0.25
    åĨľåī¯äº§åĵģ
    -0.25
    ány
    -0.25
    tics
    -0.25
     redemption
    -0.24
    POSITIVE LOGITS
     circumference
    0.28
    éĿ¢ç§¯çº¦
    0.27
    itals
    0.27
    grab
    0.27
    ç»Ī端
    0.27
    ApiClient
    0.26
    ension
    0.26
    Ùĥب
    0.25
    å±ķåİħ
    0.25
    ç»´æĮģ
    0.25
    Activations Density 0.911%

    No Known Activations