© 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. 21642
    Prev
    Next
    INDEX
    Explanations

    praise for accomplishment

    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
    _Method
    -0.06
    ç¥
    -0.06
    édé
    -0.06
     mÃŃt
    -0.06
    Ïģιθ
    -0.06
    ajian
    -0.05
    å¢
    -0.05
    ansen
    -0.05
    LOSS
    -0.05
    odate
    -0.05
    POSITIVE LOGITS
    aten
    0.06
    å©
    0.06
    åĨįæİ¥åĨįåİī
    0.06
    çĶŁæĹ¥å¿«ä¹IJ
    0.05
     excel
    0.05
    åĮ¹
    0.05
    æijĬ
    0.05
    ilia
    0.05
    ä¼ĺç§Ģ
    0.05
    åİ»åĮ»éĻ¢
    0.05
    Activations Density 0.013%

    No Known Activations