© 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. 17520
    Prev
    Next
    INDEX
    Explanations

    proceed or continue

    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
    ä¸įä¸ĭæĿ¥
    -0.07
    äºĴåĬ¨äº¤æµģ
    -0.07
     gib
    -0.06
     measure
    -0.06
    çľĭå¾ĹåĩºæĿ¥
    -0.06
     visibly
    -0.06
    bym
    -0.06
    addle
    -0.06
    GRA
    -0.06
    missive
    -0.06
    POSITIVE LOGITS
     proceed
    0.06
     proceeds
    0.05
     contin
    0.05
    contin
    0.05
     discontin
    0.05
    ç»ĵ论
    0.05
    继ç»Ń
    0.05
     proceeding
    0.05
    çģŃ
    0.05
    çĿ¦
    0.05
    Activations Density 0.039%

    No Known Activations