© 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. 21207
    Prev
    Next
    INDEX
    Explanations

    directed, sqrt, 0, gray

    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
    -conf
    -0.07
    ếu
    -0.07
    waard
    -0.07
    ÑĢÑĥбе
    -0.07
     zupeÅĤ
    -0.07
    laut
    -0.07
     telefon
    -0.06
    ENE
    -0.06
     tá»ij
    -0.06
    æĪ¿åľ°äº§å¼ĢåıijæľīéĻIJåħ¬åı¸
    -0.06
    POSITIVE LOGITS
    Âł
    0.06
    ing
    0.05
    ~
    0.05
    ↵
    0.05
    èįĴ
    0.05
     m
    0.05
    åıijå±ķ
    0.05
    o
    0.05
    0
    0.05
    âĢ
    0.05
    Activations Density 0.002%

    No Known Activations