© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107281
    Prev
    Next
    INDEX
    Explanations

    wanting

    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
    éĴ¢åİĤ
    -0.29
    InputChange
    -0.28
    Factory
    -0.26
     ÑĤипа
    -0.26
    its
    -0.26
    æĪij们çİ°åľ¨
    -0.25
    çŃ¾ä¸ĭ
    -0.25
     ведÑĮ
    -0.24
    .std
    -0.24
    ExceptionHandler
    -0.24
    POSITIVE LOGITS
     wishes
    0.27
    BREAK
    0.26
     desar
    0.26
    cken
    0.25
    èĦ©
    0.25
    æİĮæı¡
    0.25
    ãĥĬãĥ³
    0.24
     muá»ijn
    0.24
    æİĮæı¡äºĨ
    0.24
    atsu
    0.24
    Activations Density 0.942%

    No Known Activations