© 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. 107063
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    Negative Logits
    Me
    -0.27
    Quick
    -0.27
    çĻ¾åĪĨ
    -0.26
     thế
    -0.26
    æ¯Ľ
    -0.26
    Percent
    -0.25
    请åıĬæŶ
    -0.25
    <=
    -0.25
    æļĤ
    -0.24
     Me
    -0.24
    POSITIVE LOGITS
    ĭè¯ķ
    0.29
    ä»Ģ麽
    0.26
    好åIJĥ
    0.26
    .Comparator
    0.26
    ?action
    0.26
    ACEMENT
    0.26
    楯
    0.25
     наблÑİ
    0.25
    iciel
    0.24
     democrat
    0.24
    Activations Density 0.899%

    No Known Activations