© 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. 150219
    Prev
    Next
    INDEX
    Explanations

    mon

    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
    寿
    -0.28
    .scope
    -0.27
     infringement
    -0.27
    inka
    -0.26
     theorists
    -0.25
     antic
    -0.24
     *__
    -0.24
    aven
    -0.24
    æĹĦ
    -0.24
    ë²³
    -0.24
    POSITIVE LOGITS
    éĿŀ常好çļĦ
    0.30
    ç»ĵæŀĦæĢ§
    0.29
    çļĦæľĢä½³
    0.28
    æµģåĩº
    0.27
    aney
    0.27
    æĭį
    0.26
    thed
    0.26
    æµģ
    0.26
    æľĢä½³
    0.25
    ä¸ĢæĶ¯
    0.25
    Activations Density 0.907%

    No Known Activations