© 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. 19407
    Prev
    Next
    INDEX
    Explanations

    unlikely or unexpected pairings/contexts

    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
    åĮºåĪ«äºİ
    -0.06
    ä¸įåIJĮäºİ
    -0.06
    ent
    -0.06
    æĸ°å¢ŀ
    -0.05
    ksi
    -0.05
    çĬ¶æĢģ
    -0.05
     Arbor
    -0.05
     behavior
    -0.05
     numer
    -0.05
     curious
    -0.05
    POSITIVE LOGITS
    casts
    0.07
    ÑģÑĤеÑģÑĤвенно
    0.07
     casts
    0.06
    ibar
    0.06
    bows
    0.05
    uez
    0.05
    uteurs
    0.05
    uchte
    0.05
    åŀĭ
    0.05
    èĴ
    0.05
    Activations Density 0.010%

    No Known Activations