© 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. 20836
    Prev
    Next
    INDEX
    Explanations

    astronomical observations or type Ia supernova

    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
    éļ¨
    -0.06
    åĪĨéļĶ
    -0.06
    羣æŃ£
    -0.05
     mı
    -0.05
    éļı
    -0.05
    éļıçĿĢ
    -0.05
    åĩĿ
    -0.05
    åħ³
    -0.05
    éĢļ
    -0.05
    ÏģÏĨ
    -0.05
    POSITIVE LOGITS
    åij¨è¾¹çݯå¢ĥ
    0.07
    åij¨åĽ´çݯå¢ĥ
    0.06
    åıĬåij¨è¾¹
    0.06
     indirect
    0.06
    anc
    0.06
    æĪĸ缴æİ¥
    0.06
    rove
    0.06
    gre
    0.06
    ossi
    0.06
    resto
    0.06
    Activations Density 0.003%

    No Known Activations