© 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. 21894
    Prev
    Next
    INDEX
    Explanations

    you to

    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
    ling
    -0.05
    wi
    -0.05
    s
    -0.05
    æĦŁçļĦ
    -0.05
    bel
    -0.05
    ones
    -0.05
    uy
    -0.05
    indre
    -0.05
     dahulu
    -0.05
    ë¶Ģ를
    -0.05
    POSITIVE LOGITS
    ä¸įäºĨ
    0.07
     Bagus
    0.07
    orsch
    0.06
    CLUDING
    0.06
    æ´»åĬ¨åľºæīĢ
    0.06
    ivec
    0.06
    ACHI
    0.06
    bereit
    0.06
    itano
    0.06
    तà¥į
    0.06
    Activations Density 0.008%

    No Known Activations