© 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. 21802
    Prev
    Next
    INDEX
    Explanations

    generalize

    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
    aline
    -0.05
    quot
    -0.05
    engel
    -0.05
    hog
    -0.05
     tand
    -0.05
     only
    -0.05
    ç»ĨåĪĻ
    -0.05
    æĹłéĿŀ
    -0.05
    æľīä¸ĭåĪĹ
    -0.05
    å±ŀäºİ
    -0.05
    POSITIVE LOGITS
    æĸ°æ¦Ĥ念
    0.08
    æĸ¹ä¾¿çļĦ
    0.08
     corresp
    0.06
     broader
    0.06
     generalize
    0.06
    缸å½ĵäºİ
    0.06
     koncep
    0.06
     unify
    0.06
    豪
    0.06
    åĩĮ空
    0.06
    Activations Density 0.098%

    No Known Activations