© 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. 107573
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     reliance
    -0.26
    broken
    -0.24
    achinery
    -0.24
    éĿĴ
    -0.24
     Sticky
    -0.24
    çĤ¹èµŀ
    -0.24
    Powered
    -0.24
    :host
    -0.24
    bond
    -0.23
    èĥĮåIJİ
    -0.23
    POSITIVE LOGITS
    ürü
    0.27
    ÙĤب
    0.27
     nắng
    0.26
    law
    0.26
    ëĮĢíķĻ
    0.25
    atin
    0.25
    getParam
    0.25
    åĵ¥ä¼¦æ¯Ķäºļ
    0.25
    ilor
    0.25
     -------------------------------------------------------------------------
    0.25
    Activations Density 1.000%

    No Known Activations

    This feature has no known activations.