© 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. 141244
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    tle
    -0.26
    泡
    -0.26
    midi
    -0.25
    amenti
    -0.25
    çļĦå¢ŀéķ¿
    -0.25
    mist
    -0.24
    æ·±åħ¥äººå¿ĥ
    -0.24
    mph
    -0.23
    emons
    -0.23
     clinic
    -0.23
    POSITIVE LOGITS
    aus
    0.28
     Ngh
    0.27
    cker
    0.26
    eren
    0.26
    å¥ĩ
    0.25
    å¼Ĥåľ°
    0.25
    论è¯ģ
    0.25
    æ³ģ
    0.25
     rÃłng
    0.25
    ypy
    0.24
    Activations Density 25.282%

    No Known Activations