© 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. 21056
    Prev
    Next
    INDEX
    Explanations

    vehicle wraps

    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
     concierto
    -0.07
    ä¼Łä¸ļ
    -0.07
     Purtroppo
    -0.07
     Ovviamente
    -0.07
    cich
    -0.06
    nent
    -0.06
    nen
    -0.06
    çĻ½æĹ¥
    -0.06
    acades
    -0.06
    ãģ«è¡Įãģ£ãģ¦ãģįãģ¾ãģĹãģŁ
    -0.06
    POSITIVE LOGITS
    çŃī
    0.05
     fr
    0.05
     dimin
    0.05
     gran
    0.05
     Gran
    0.05
     as
    0.05
    0.05
     ir
    0.05
     v
    0.05
     p
    0.04
    Activations Density 0.065%

    No Known Activations