© 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. 15188
    Prev
    Next
    INDEX
    Explanations

    setting limits or caps

    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
    ಣ
    -0.08
    æŀ«
    -0.08
    æĢģ
    -0.07
    habit
    -0.07
    HashCode
    -0.07
    rafos
    -0.07
    trze
    -0.07
    veys
    -0.07
    ONO
    -0.07
    ĸ
    -0.07
    POSITIVE LOGITS
    éĻIJåĪ¶
    0.19
    éĻIJåĪ¶çļĦ
    0.17
     limits
    0.17
    约æĿŁ
    0.17
     limiting
    0.17
     limitation
    0.17
     constraints
    0.17
     limit
    0.16
    éĻIJåĪ¶äºĨ
    0.16
     limitations
    0.16
    Activations Density 0.097%

    No Known Activations