© 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. 17106
    Prev
    Next
    INDEX
    Explanations

    muscular

    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
    -return
    -0.05
    olve
    -0.05
    pn
    -0.05
    ëĵłì§Ģ
    -0.05
    pts
    -0.05
    olt
    -0.05
    OLT
    -0.05
     muted
    -0.05
    åĽŀ
    -0.05
    át
    -0.05
    POSITIVE LOGITS
    elio
    0.07
    enin
    0.07
     gewissen
    0.07
    reas
    0.07
    aimana
    0.07
    ÙĥÙĬÙħ
    0.06
    ly
    0.06
    à¹Į
    0.06
    è¢«æŁ¥
    0.06
    ä½ľæ³ķ
    0.06
    Activations Density 0.001%

    No Known Activations