© 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. 20935
    Prev
    Next
    INDEX
    Explanations

    sexual and violent acts

    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
    ienes
    -0.06
     snug
    -0.06
    itik
    -0.06
    _way
    -0.06
     aforementioned
    -0.06
    igent
    -0.06
    è·ŁæĪij说
    -0.06
     Estates
    -0.06
    icht
    -0.05
    æ¯ķ
    -0.05
    POSITIVE LOGITS
    ÙĨدÙĩ
    0.06
     grown
    0.05
    us
    0.05
    ä¼´
    0.05
    —even
    0.05
     permission
    0.05
    ä»ħ
    0.05
    vai
    0.05
     cens
    0.05
    iron
    0.05
    Activations Density 0.003%

    No Known Activations