© 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. 17432
    Prev
    Next
    INDEX
    Explanations

    picture of

    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
    éĿŀ常å¤ļçļĦ
    -0.06
    æĢ§ãģ¯
    -0.05
    èĢħçļĦ
    -0.05
    èĢħ们
    -0.05
    æĹ¥æĻļéĹ´
    -0.05
    æĢ§ãģ«
    -0.05
    ieke
    -0.05
     sû
    -0.05
    åİĭåĻ¨
    -0.05
     judging
    -0.05
    POSITIVE LOGITS
     myself
    0.07
    ussen
    0.06
    arsing
    0.06
    ÏĢοÏħ
    0.06
    andu
    0.06
    물ìĿ´
    0.06
    å§Ĩ
    0.06
    wm
    0.06
    bum
    0.06
    ething
    0.06
    Activations Density 0.033%

    No Known Activations