© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34958
    Prev
    Next
    INDEX
    Explanations

    forgiveness and acceptance

    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
    Negative Logits
     timid
    -0.07
    éĢĥåĩº
    -0.07
    æ¿Ĵåį±
    -0.07
    饿
    -0.07
    éĢĥ
    -0.06
    è¿«ä¸įåıĬå¾ħ
    -0.06
    å¯Ĩå¯Ĩ麻麻
    -0.06
    çĶŁæĢķ
    -0.06
    è¿«ä¸įåıĬå¾ħåľ°
    -0.06
    çĬ¹è±«
    -0.06
    POSITIVE LOGITS
    è±ģè¾¾
    0.14
    ä¹IJ天
    0.13
     accepting
    0.13
     acceptance
    0.13
    å¿ĥæĢģ
    0.12
     tolerance
    0.12
     Accept
    0.12
     tolerant
    0.11
    Accept
    0.11
    tol
    0.11
    Activations Density 0.142%

    No Known Activations