© 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. 18286
    Prev
    Next
    INDEX
    Explanations

    como / how / o que

    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
    abor
    -0.07
    arna
    -0.07
    uate
    -0.07
    ingly
    -0.07
    ÙĪØ©
    -0.07
    جÙħعÙĬØ©
    -0.07
    ures
    -0.07
    itt
    -0.07
    ÙĦÙĩ
    -0.07
    jähr
    -0.07
    POSITIVE LOGITS
    를
    0.08
    çļĦ
    0.06
    æĸ°åĬłåĿ¡
    0.05
    пеÑĢвÑĭе
    0.05
    ë¡ľ
    0.05
    åĬłæĭ¿å¤§
    0.05
    ystery
    0.05
    µ
    0.04
    spre
    0.04
    nance
    0.04
    Activations Density 0.002%

    No Known Activations