© 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. 130366
    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
    说æĺİ
    -0.29
     ÑģпоÑģоб
    -0.27
    å¿«ä¹IJ
    -0.26
    çĶŁæĢķ
    -0.25
    èĢĨ
    -0.24
    ç¼µ
    -0.24
    -talk
    -0.24
    tie
    -0.23
    zi
    -0.23
     experienced
    -0.23
    POSITIVE LOGITS
    éĥ½æĺ¯éĿŀ常
    0.27
    falls
    0.27
    inkel
    0.26
    ditor
    0.25
    ény
    0.24
    enus
    0.24
    epy
    0.24
    éĥ½å¾Ī
    0.24
     Bry
    0.24
    æıIJ款
    0.24
    Activations Density 5.483%

    No Known Activations