© 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. 17949
    Prev
    Next
    INDEX
    Explanations

    admitting to wrongdoing or pain

    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
     hastily
    -0.05
    orman
    -0.05
    æĽ´åĬłæ³¨éĩį
    -0.05
    GW
    -0.05
    çĿĢäºĨ
    -0.05
    çĤºæĤ¨
    -0.05
     frankly
    -0.05
     confia
    -0.05
    áz
    -0.05
     Siège
    -0.05
    POSITIVE LOGITS
    款çļĦ
    0.06
    olecules
    0.06
    å°Ĭ
    0.06
    ç«ĭ
    0.06
    ullo
    0.06
    èģļ
    0.06
     yell
    0.06
     обÑīение
    0.06
    —including
    0.06
    Sharp
    0.05
    Activations Density 0.004%

    No Known Activations