© 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. 46389
    Prev
    Next
    INDEX
    Explanations

    thresholds and conditions

    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
    enso
    -0.09
    ôm
    -0.07
    ields
    -0.07
    çŃ¾åĪ°
    -0.07
    èĢĮå½Ĵ
    -0.07
    èĢĮä¸įè§ģ
    -0.07
    .unknown
    -0.07
    _inputs
    -0.07
    çŁ¥éģĵ大æľīåı¯ä¸ºçŃĶ主
    -0.07
    æ¬łæĿ¡
    -0.06
    POSITIVE LOGITS
    éĹ¨æ§Ľ
    0.09
    åı¯è¡ĮæĢ§
    0.09
     viable
    0.09
    è´¹
    0.08
     feasibility
    0.08
     thresholds
    0.08
    å¼ĢæĶ¾
    0.08
     threshold
    0.08
     driven
    0.08
    Threshold
    0.08
    Activations Density 0.001%

    No Known Activations