© 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. 17388
    Prev
    Next
    INDEX
    Explanations

    sensitive topics and issues

    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
    ấp
    -0.06
    第äºĮçĻ¾éĽ¶
    -0.06
    ixel
    -0.05
    åıijç»Ļ
    -0.05
    anning
    -0.05
    è´Łæľī
    -0.05
    æĿ¯æ°´
    -0.05
    Character
    -0.05
    enzhen
    -0.05
    ä»»ä½ķ人
    -0.05
    POSITIVE LOGITS
     emot
    0.07
    ahu
    0.06
    abia
    0.06
    çļĦç¼ĺæķħ
    0.06
    iegész
    0.06
    umas
    0.05
    unte
    0.05
     emotions
    0.05
    got
    0.05
    _AB
    0.05
    Activations Density 0.003%

    No Known Activations