© 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. 107350
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ä¹Łå¥½
    -0.35
    缺ä¹ı
    -0.30
    ä¸į管
    -0.28
    Whatever
    -0.27
     complains
    -0.26
     whichever
    -0.26
     complained
    -0.26
    eras
    -0.26
    ียว
    -0.25
    eden
    -0.25
    POSITIVE LOGITS
     Cald
    0.27
    iffany
    0.27
    æīĭæľº
    0.27
    atl
    0.26
    (IF
    0.26
    eya
    0.25
    æ²
    0.25
     Cursors
    0.25
    PERT
    0.24
     Tie
    0.24
    Activations Density 34.900%

    No Known Activations