© 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. 17562
    Prev
    Next
    INDEX
    Explanations

    musicians and singers

    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
    åIJ»
    -0.05
    éĢĶ
    -0.05
    çĤ¹åŃIJ
    -0.05
    ÙĪÙĩ
    -0.05
    osten
    -0.05
    èĦij
    -0.05
    çĻĸ
    -0.05
    Ùģ
    -0.05
    alem
    -0.05
    è·ĥè¿Ľ
    -0.05
    POSITIVE LOGITS
    æİĴè¡Į
    0.06
    igure
    0.06
    ilk
    0.06
    imary
    0.06
    åįĥç§ĭ
    0.06
    ức
    0.06
    æ¹Ľ
    0.05
    vere
    0.05
    azzi
    0.05
     пов
    0.05
    Activations Density 0.010%

    No Known Activations