© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19945
    Prev
    Next
    INDEX
    Explanations

    API documentation

    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
    à¸Ħ
    -0.06
    oola
    -0.05
    ilo
    -0.05
    lic
    -0.05
    Ïģε
    -0.05
    engen
    -0.05
    è½®
    -0.05
    ASS
    -0.05
    çļĦ表çİ°
    -0.05
    iger
    -0.05
    POSITIVE LOGITS
    ç½®åľ°
    0.06
    زاÙħ
    0.06
    bose
    0.06
    ç§ijæĬĢæľīéĻIJ责任åħ¬åı¸
    0.06
    缮ä¸Ń
    0.06
    [âĢ¦
    0.06
    crap
    0.06
    说æľī
    0.05
    à¸ŀิà¹Ģศษ
    0.05
    eret
    0.05
    Activations Density 0.003%

    No Known Activations