© 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. 24-TRANSCODER-HP
    7. 150608
    Prev
    Next
    INDEX
    Explanations

    ian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ily
    -0.28
    wig
    -0.27
    icket
    -0.26
     triples
    -0.24
    -wise
    -0.24
    wipe
    -0.24
     whip
    -0.24
     knocks
    -0.24
    ertz
    -0.23
    çļĦæĸ¹å¼ıæĿ¥
    -0.23
    POSITIVE LOGITS
    hana
    0.33
    isser
    0.27
     vs
    0.26
     +++
    0.25
     pragma
    0.25
    Fullscreen
    0.24
     Novel
    0.24
    +++
    0.23
    å·²ç»ı被
    0.23
    strt
    0.23
    Activations Density 0.145%

    No Known Activations