© 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. 20-TRANSCODER-HP
    7. 108299
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocking
    -0.27
    ctal
    -0.27
     Mime
    -0.25
    arbon
    -0.25
    unce
    -0.25
    ục
    -0.25
    级以ä¸Ĭ
    -0.25
    ãģķãĤĮãģ¾ãģĹãģŁ
    -0.24
    actors
    -0.24
    arness
    -0.24
    POSITIVE LOGITS
    éĶħ
    0.26
    æĹºåŃ£
    0.25
     saber
    0.25
     quân
    0.25
    éĶĻ
    0.24
    åı¦ä¸Ģè¾¹
    0.24
    æľīéĻIJ
    0.24
    ”↵↵
    0.24
     retal
    0.24
    Mid
    0.23
    Activations Density 0.874%

    No Known Activations