© 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. 21449
    Prev
    Next
    INDEX
    Explanations

    AM/PM time indicators

    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
     NotImplemented
    -0.07
    æĿ¡æĿ¡
    -0.06
    ä¸įåĪ©
    -0.06
    çī¹éķ¿
    -0.06
     пÑĢоÑĤивопо
    -0.06
    ATEN
    -0.06
    esm
    -0.06
    éĽį
    -0.06
     Polis
    -0.06
    imar
    -0.06
    POSITIVE LOGITS
    cock
    0.05
     faith
    0.05
     authentic
    0.05
    Ñħод
    0.05
     truly
    0.05
     fat
    0.05
     J
    0.05
     properly
    0.05
     shades
    0.05
    faith
    0.05
    Activations Density 0.011%

    No Known Activations