© 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. 17629
    Prev
    Next
    INDEX
    Explanations

    vendor promise

    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
    lem
    -0.06
    MT
    -0.06
    plan
    -0.06
     contrario
    -0.05
    UMP
    -0.05
    lems
    -0.05
    loat
    -0.05
    issen
    -0.05
     N
    -0.05
    à¸Ĺà¹Į
    -0.05
    POSITIVE LOGITS
    мееÑĤÑģÑı
    0.09
    enje
    0.07
    为äºĨ解åĨ³
    0.07
    缺
    0.06
    exécution
    0.06
    Ïģεία
    0.06
    ä¸Ģå¥Ĺ
    0.06
    espace
    0.06
    bliż
    0.06
    wing
    0.06
    Activations Density 0.004%

    No Known Activations