© 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. 107913
    Prev
    Next
    INDEX
    Explanations

    university, research

    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
    adar
    -0.28
    pos
    -0.26
    ptom
    -0.25
    绣çŃ¹
    -0.25
     sensit
    -0.25
     cyber
    -0.24
     mesh
    -0.24
     cockpit
    -0.24
     crest
    -0.24
    meter
    -0.24
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.32
    æīįåı¯ä»¥
    0.30
    research
    0.28
     sammen
    0.27
    论æĸĩ
    0.27
    çłĶ究
    0.26
    ç§ijåѦçłĶ究
    0.26
     researched
    0.26
    æķ°æį®æĺ¾ç¤º
    0.26
    çłĶ究æĪIJæŀľ
    0.25
    Activations Density 0.120%

    No Known Activations