© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49422
    Prev
    Next
    INDEX
    Explanations

    disclosed, confirm, compensation, grateful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é«ĺä¸ŃçļĦ
    -0.08
    ä¾¥
    -0.08
    iliar
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    å§ĭèĩ³
    -0.07
    olan
    -0.07
    åĬłåħ¥ä¹¦çŃ¾
    -0.07
    oko
    -0.07
    ignan
    -0.07
    POSITIVE LOGITS
    åij±
    0.08
    etter
    0.07
     acknowledges
    0.07
     acknowledged
    0.07
    éĺħè¯»æľ¬æĸĩ
    0.07
    ×ķר×ķת
    0.07
    itchens
    0.06
     unrelated
    0.06
    opat
    0.06
    åķĬåķĬ
    0.06
    Activations Density 0.040%

    No Known Activations