© 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. 17177
    Prev
    Next
    INDEX
    Explanations

    cautionary concepts

    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
     gesta
    -0.06
     continuation
    -0.06
    é»ĦçīĽ
    -0.06
    zaak
    -0.06
     Frat
    -0.05
    çļĦå¿ĥ声
    -0.05
    ØŃÙħ
    -0.05
    _legacy
    -0.05
    Dat
    -0.05
    ä¾Ŀæ³ķ追究责任
    -0.05
    POSITIVE LOGITS
    inf
    0.06
     })(
    0.06
    Âł
    0.06
    artos
    0.05
    ault
    0.05
    inian
    0.05
    ä¸į计
    0.05
    igger
    0.05
    å±ij
    0.05
    è¯ij
    0.05
    Activations Density 0.007%

    No Known Activations