© 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. 21072
    Prev
    Next
    INDEX
    Explanations

    FIRST TEST

    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
    ãģªãģį
    -0.06
     burge
    -0.06
    é£İ顺
    -0.06
     ØŃرص
    -0.06
    гина
    -0.06
    å¿ĥ缮
    -0.06
    é¢Ħç¥Ŀ
    -0.06
     frais
    -0.05
    没æľīåľ¨
    -0.05
    使çĶ¨å¹´éĻIJ
    -0.05
    POSITIVE LOGITS
     ar
    0.06
     bas
    0.05
    ÙĪد
    0.05
    eke
    0.05
     clin
    0.05
    ä¸įç®Ĺ
    0.05
     little
    0.05
    æľĢåIJİçļĦ
    0.05
     sh
    0.05
     final
    0.05
    Activations Density 0.006%

    No Known Activations