© 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. 20619
    Prev
    Next
    INDEX
    Explanations

    I need to see that better

    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
    äº
    -0.05
    à¹ģà¸ĩ
    -0.05
    innan
    -0.05
    俱
    -0.05
    æĺ¯æľī
    -0.05
     sü
    -0.05
    å¤Ń
    -0.05
    åŃIJç³»ç»Ł
    -0.05
    æ¸ħåįķ
    -0.05
    нан
    -0.05
    POSITIVE LOGITS
    åħ¶èģĮ
    0.07
     Consort
    0.06
    èĭ±æĸĩåŃĹ
    0.06
    oad
    0.06
    ä¹Łä¸į太
    0.06
    常è§ģçĹħ
    0.06
    orme
    0.06
    ï¸İ
    0.06
     **âĢ¢
    0.06
     matrimon
    0.06
    Activations Density 0.021%

    No Known Activations