© 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. 21545
    Prev
    Next
    INDEX
    Explanations

    in the dark

    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
    缴æİ¥ä¸İ
    -0.06
    缴æİ¥æĬĬ
    -0.06
    æĬĺ
    -0.06
    åħ¸
    -0.06
    adop
    -0.05
     ведÑĮ
    -0.05
    atto
    -0.05
    à¸ĵา
    -0.05
    çĤĻ
    -0.05
    ç»Ŀ
    -0.05
    POSITIVE LOGITS
     therein
    0.06
    ôme
    0.06
    iose
    0.06
    opan
    0.05
    uddy
    0.05
    æĺµç§°
    0.05
    ä¼Ļ
    0.05
    ine
    0.05
    çļĦç½ij绾
    0.05
    ummy
    0.05
    Activations Density 0.011%

    No Known Activations