© 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. 149838
    Prev
    Next
    INDEX
    Explanations

    words of other languages

    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
    夹
    -0.29
    ponsive
    -0.27
    football
    -0.25
    olle
    -0.25
     KeyboardInterrupt
    -0.25
    æĮ¡
    -0.24
    té
    -0.24
    çļĦä¼ĺçĤ¹
    -0.23
    illin
    -0.23
    çļĦä¼ĺåĬ¿
    -0.23
    POSITIVE LOGITS
    累计
    0.45
    æĢ»æķ°
    0.40
    æĢ»è®¡
    0.39
     cumulative
    0.37
     total
    0.36
     totals
    0.35
     Total
    0.35
    累积
    0.34
    ctxt
    0.34
    ç»Łè®¡
    0.33
    Activations Density 1.107%

    No Known Activations