© 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. 23-TRANSCODER-HP
    7. 23800
    Prev
    Next
    INDEX
    Explanations

    Time duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĤ¨çļĦåŃ©åŃIJ
    -0.26
     kidding
    -0.26
     eq
    -0.25
    å¹²äºĭ
    -0.24
    lad
    -0.24
     ste
    -0.24
    åī§ä¸Ń
    -0.24
     Foods
    -0.24
    <u
    -0.24
    æµĨ
    -0.24
    POSITIVE LOGITS
    ç»ıéªĮåĴĮ
    0.35
    ç»ıéªĮ
    0.34
    çļĦç»ıéªĮ
    0.34
    ç»ıéªĮ丰å¯Į
    0.32
    éĺħåİĨ
    0.31
    å·¥ä½ľç»ıéªĮ
    0.30
    å®ŀè·µç»ıéªĮ
    0.29
     experience
    0.29
    experience
    0.28
    è¿Ħä»Ĭ
    0.28
    Activations Density 0.039%

    No Known Activations