© 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. 18097
    Prev
    Next
    INDEX
    Explanations

    Aristotle, virtue, ideas

    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
     trav
    -0.05
    ä»Ļå¢ĥ
    -0.05
    .locale
    -0.05
    åĬłæ·±
    -0.05
    XS
    -0.05
    ierge
    -0.05
    initi
    -0.05
    ç»®
    -0.05
    æľĿ
    -0.05
    BERS
    -0.05
    POSITIVE LOGITS
     Aristotle
    0.07
    fus
    0.06
    åºŁè¯Ŀ
    0.06
    .od
    0.06
    otle
    0.06
    ipy
    0.06
    porta
    0.06
    è¿ĻéŨ
    0.06
    å¾Ħ
    0.06
    å°±åľ°
    0.06
    Activations Density 0.002%

    No Known Activations