© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20979
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hetnek
    -0.06
    éĢĢ
    -0.06
    vang
    -0.06
    qip
    -0.05
    èĥĮæĻ¯åĴĮ
    -0.05
    eneg
    -0.05
    æĸ¹å¼ı使çĶ¨
    -0.05
    vende
    -0.05
    åİŁä»¶åıĬå¤įåį°ä»¶
    -0.05
    halt
    -0.05
    POSITIVE LOGITS
    du
    0.06
    inish
    0.06
    ppe
    0.05
    pery
    0.05
    rael
    0.05
    ific
    0.05
     foss
    0.05
    WISE
    0.05
    ius
    0.05
    rh
    0.05
    Activations Density 0.002%

    No Known Activations