© 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. 18384
    Prev
    Next
    INDEX
    Explanations

    state of being

    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
     Oto
    -0.06
    è®Ń
    -0.06
    è¨ĵ
    -0.05
    ÙĪائ
    -0.05
     rec
    -0.05
     poc
    -0.05
    åŃĺæĶ¾åľ¨
    -0.05
    ÙĤر
    -0.05
    اد
    -0.05
    alan
    -0.05
    POSITIVE LOGITS
    çļĦ身影
    0.07
    ikov
    0.06
    羣çļĦ
    0.06
    iecz
    0.06
    çĶļèĩ³è¿ĺæľī
    0.05
     vorba
    0.05
    ÑĢенда
    0.05
    æķ°æį®æĿ¥æºIJ
    0.05
     conlle
    0.05
     gigante
    0.05
    Activations Density 0.051%

    No Known Activations