© 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. 64049
    Prev
    Next
    INDEX
    Explanations

    permitted / prohibited

    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
    æ¯ı次éĥ½
    -0.08
    esse
    -0.08
    åĽłæĿIJ
    -0.07
    åľ¨çº¿åĴ¨è¯¢
    -0.07
     Batch
    -0.07
     Targets
    -0.07
    ctr
    -0.07
    åľ°é»Ħ
    -0.07
    ç«ĭæ¡Īä¿¡æģ¯
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    POSITIVE LOGITS
     permitted
    0.11
    带åħ¥
    0.10
    _allowed
    0.09
    带äºĨ
    0.09
    Allowed
    0.09
    èĩªå¤ĩ
    0.09
     allowed
    0.09
     ÑĢазÑĢеÑĪ
    0.09
     prohibited
    0.08
    èĩªå¸¦
    0.08
    Activations Density 0.096%

    No Known Activations