© 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. 17282
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

    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
    éĸ£
    -0.06
    çİĩåĴĮ
    -0.06
    URS
    -0.06
     Fantas
    -0.06
    orts
    -0.06
    æѤæĸĩ
    -0.06
    óri
    -0.06
    alz
    -0.06
    çļĦåħ´è¶£
    -0.06
    åĮºäººæ°ijæ³ķéĻ¢
    -0.06
    POSITIVE LOGITS
    hand
    0.05
    ler
    0.05
    oh
    0.05
    uela
    0.05
    yu
    0.05
    ak
    0.05
    anza
    0.05
    广ä¹ī
    0.05
    ÑıÑĤо
    0.05
    ker
    0.05
    Activations Density 0.011%

    No Known Activations