© 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. 150812
    Prev
    Next
    INDEX
    Explanations

    Common words/code

    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
    ificantly
    -0.28
    ität
    -0.28
    æĢ§å¼º
    -0.26
    æŶéĹ´åĨħ
    -0.25
    NEY
    -0.25
    -License
    -0.25
    itÃł
    -0.25
    plx
    -0.25
    /autoload
    -0.25
    åħģ
    -0.25
    POSITIVE LOGITS
    çļĦæĪ¿åŃIJ
    0.34
    çļĦè¡£æľį
    0.32
    çļĦèĥ½éĩı
    0.30
    çļĦæĥħ绪
    0.29
    æĪijçļĦå¿ĥ
    0.28
    ute
    0.28
    ur
    0.28
    utra
    0.28
    nh
    0.27
    rf
    0.26
    Activations Density 0.965%

    No Known Activations