© 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. 108330
    Prev
    Next
    INDEX
    Explanations

    scientific and technical texts

    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
    (['/
    -0.28
    oid
    -0.28
    clearfix
    -0.27
    æĺ¯ä¸Ģ
    -0.27
    西æĸ¹
    -0.26
    ronic
    -0.25
    weet
    -0.25
    å¤ļç§įå½¢å¼ı
    -0.25
    æĺ¯ä¸Ģ项
    -0.25
     WC
    -0.24
    POSITIVE LOGITS
    tesy
    0.25
     MIT
    0.25
    outine
    0.24
     *(*
    0.23
    -.
    0.23
    触
    0.23
    ISODE
    0.23
    æĪĺçķ¥æĢ§
    0.23
     association
    0.23
    è±ģ
    0.23
    Activations Density 1.068%

    No Known Activations