© 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. 21283
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
    ÑįÑĤ
    -0.06
     ales
    -0.06
    -most
    -0.05
    elli
    -0.05
    à¥Įर
    -0.05
    许
    -0.05
    ello
    -0.05
    Hints
    -0.05
     contraire
    -0.05
    ry
    -0.05
    POSITIVE LOGITS
     hag
    0.07
    ä»ĬæĹ¥çļĦ
    0.06
    æĸ°åĬłåĿ¡
    0.06
    对å®ĥ
    0.06
    åı£ä¸ŃçļĦ
    0.06
    ')</
    0.06
    æĨij
    0.06
    ÃĹ</
    0.06
    NSURL
    0.06
    bose
    0.06
    Activations Density 0.055%

    No Known Activations