© 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. 17752
    Prev
    Next
    INDEX
    Explanations

    psychopathology and conduct disorder

    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
    ®
    -0.06
     flux
    -0.05
    çĦ¦èĻij
    -0.05
    ç¦»æł¡
    -0.05
    æĻ¦
    -0.05
    inta
    -0.05
    flux
    -0.05
    ourney
    -0.05
     Flux
    -0.05
     Messenger
    -0.05
    POSITIVE LOGITS
    ahan
    0.06
    inom
    0.06
    ÑĨе
    0.06
    å·¥åİĤ
    0.06
    abar
    0.06
    åģĩ
    0.06
    æ¼ł
    0.06
     attent
    0.06
     basi
    0.06
    ossa
    0.06
    Activations Density 0.003%

    No Known Activations