© 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. 17821
    Prev
    Next
    INDEX
    Explanations

    speed, duration, state, SD, hours

    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
    ancel
    -0.07
    ÑīноÑģÑĤÑĮ
    -0.07
    stral
    -0.06
    jons
    -0.06
    æīįæľīåı¯èĥ½
    -0.06
    yanto
    -0.06
    innie
    -0.06
     Cie
    -0.06
    é«ĺçŃī
    -0.05
    ans
    -0.05
    POSITIVE LOGITS
     er
    0.06
    æ¸Ĭ
    0.06
    çĥŃéŨæݨèįIJ
    0.05
    HH
    0.05
    äºİ人
    0.05
     com
    0.05
     de
    0.05
    å¦Ĥä¸ĭ
    0.05
    моÑĤ
    0.05
     rob
    0.05
    Activations Density 0.085%

    No Known Activations