© 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. 107370
    Prev
    Next
    INDEX
    Explanations

    code/file paths

    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
    åı¯æĥ³
    -0.29
     benef
    -0.27
     prom
    -0.26
     ste
    -0.25
     bypass
    -0.25
    amy
    -0.24
    ornado
    -0.24
    [op
    -0.24
    istar
    -0.24
     characterized
    -0.24
    POSITIVE LOGITS
    æ¯ķç«Ł
    0.31
    æµģè¡ĮçļĦ
    0.30
    éĩĮçļĦ
    0.29
    é»į
    0.27
    å¼ıçļĦ
    0.27
    éĩĮéĿ¢çļĦ
    0.27
    è¯ģåĪ¸äº¤æĺĵ
    0.26
    çķ¢ç«Ł
    0.26
    游æĪıä¸Ń
    0.26
    çĶŁäº§çļĦ
    0.25
    Activations Density 1.147%

    No Known Activations