© 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. 22049
    Prev
    Next
    INDEX
    Explanations

    L10N

    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
    ung
    -0.06
    ı
    -0.06
    æŦ
    -0.06
    ÂŃ
    -0.05
    æ´¾çļĦ
    -0.05
     .
    -0.05
    <|object_ref_end|>
    -0.05
    IS
    -0.05
    ï
    -0.05
    -0.05
    POSITIVE LOGITS
    ãģ¾ãģĹãģŁ
    0.07
    é¨ĵ
    0.07
    entras
    0.07
    ÑģÑĤÑĮÑİ
    0.07
    ebil
    0.07
    lients
    0.06
     ìłĦë§ĿìĿ´ëĭ¤
    0.06
    perk
    0.06
    ãģĭãģ£ãģŁãģ®ãģ§
    0.06
    Lint
    0.06
    Activations Density 0.011%

    No Known Activations