© 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. 17091
    Prev
    Next
    INDEX
    Explanations

    back to

    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
    گرÛĮ
    -0.07
    impat
    -0.07
    **(
    -0.06
    æŃ¤æ¬¾
    -0.06
    æľĪçĶŁ
    -0.06
    å°ĨæѤ
    -0.06
    æĥ³å¾Ĺ
    -0.06
    ä½łä»¬éĥ½
    -0.06
    èĭŁ
    -0.06
    ãģĨãģ¡
    -0.06
    POSITIVE LOGITS
    TRUE
    0.06
    æ³Ľ
    0.06
    ï¸ı
    0.06
    i
    0.06
    imum
    0.05
    ature
    0.05
     downt
    0.05
    iode
    0.05
    erman
    0.05
     combusti
    0.05
    Activations Density 0.011%

    No Known Activations