© 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. 19963
    Prev
    Next
    INDEX
    Explanations

    game titles

    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
    <
    -0.06
    -0.05
    ä¸ĵ
    -0.05
     <
    -0.05
     wield
    -0.05
     Bias
    -0.05
    /
    -0.05
    ä¸ĵéŨ
    -0.05
    -
    -0.05
    好çĶ¨
    -0.05
    POSITIVE LOGITS
    çī½
    0.07
    è¦ģæ±Ĥè¿Ľè¡Į
    0.07
    çºĮ
    0.07
    tika
    0.07
    ÑģÑĤеÑģÑĤвенно
    0.07
    irão
    0.07
    eningen
    0.06
    æģ¯çļĦ
    0.06
    æĮģç»ŃçļĦ
    0.06
    ULLET
    0.06
    Activations Density 0.029%

    No Known Activations