© 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. 33199
    Prev
    Next
    INDEX
    Explanations

    acting and character authenticity

    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
    举èĩ³
    -0.07
    享
    -0.07
    ikk
    -0.07
    æ¸ħåĩĢ
    -0.07
     protected
    -0.06
     enjoyed
    -0.06
    éĺ³æĢ§
    -0.06
     Enjoy
    -0.06
    HEL
    -0.06
     Protected
    -0.06
    POSITIVE LOGITS
     believable
    0.10
    羣å®ŀçļĦ
    0.09
     authenticity
    0.09
    丰满
    0.09
     realism
    0.09
     empathy
    0.08
     subtle
    0.08
     convinc
    0.08
     nuanced
    0.08
    æł©æł©å¦Ĥ
    0.08
    Activations Density 0.039%

    No Known Activations