© 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. 18214
    Prev
    Next
    INDEX
    Explanations

    free time

    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
    å¨ĺ
    -0.05
    å¼¥
    -0.05
    quent
    -0.05
    æĸŃ
    -0.05
     Cort
    -0.04
    aine
    -0.04
     temperature
    -0.04
    -
    -0.04
    chl
    -0.04
    oder
    -0.04
    POSITIVE LOGITS
     regr
    0.07
    ajari
    0.07
    (mappedBy
    0.06
    æĥ³æĸ¹
    0.06
    íķ´
    0.06
    åĬĽä½ľ
    0.06
    жела
    0.06
    ftime
    0.06
     malah
    0.06
    конÑģÑĥлÑĮÑĤи
    0.06
    Activations Density 0.006%

    No Known Activations