© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61964
    Prev
    Next
    INDEX
    Explanations

    jr. junior family members

    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
    èĢģæľĭåıĭ
    -0.11
    èĢģ人家
    -0.09
    èĢģåıĭ
    -0.09
    ä¹ĭä¹ħ
    -0.08
    wives
    -0.08
    éĢĢä¼ij
    -0.08
    éĢĢä¼ij人åijĺ
    -0.08
    wife
    -0.08
    çļĦ女人
    -0.07
    好人
    -0.07
    POSITIVE LOGITS
     inher
    0.17
     inherit
    0.17
    继æī¿
    0.17
    继æī¿äºĨ
    0.16
     inherits
    0.16
    inherit
    0.15
     inheritance
    0.15
     inherited
    0.14
    éķ¿å¤§äºĨ
    0.14
    ç¹¼æī¿
    0.14
    Activations Density 0.766%

    No Known Activations