© 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. 22039
    Prev
    Next
    INDEX
    Explanations

    game state

    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
     chance
    -0.06
    i
    -0.06
    æīĢ
    -0.05
     bet
    -0.05
    f
    -0.05
     bert
    -0.05
    u
    -0.05
    æĸ°åħ´
    -0.05
    é¦ĸä½į
    -0.05
    ãģĶ
    -0.05
    POSITIVE LOGITS
     incontourn
    0.07
     ())
    0.07
    æľīä¸įåIJĮçļĦ
    0.07
    accompagn
    0.07
    éģ¸äºº
    0.06
    ].'
    0.06
    éĶ¦æ¶Ľ
    0.06
    ä¸ĢåĢĭ人
    0.06
     interns
    0.06
     Condizioni
    0.06
    Activations Density 0.010%

    No Known Activations