© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22588
    Prev
    Next
    INDEX
    Explanations

    rules, constitution, guidelines

    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
    åºĶéħ¬
    -0.08
    lø
    -0.07
    çīĪæĿĥæīĢæľī
    -0.07
    积æŀģåĪĨåŃIJ
    -0.07
    æ¬²æľĽ
    -0.07
    rawy
    -0.07
    ä¸įåı¯æĢķ
    -0.07
    åĸľæĢĴ
    -0.07
    IAM
    -0.07
    æĹ©å®ī
    -0.07
    POSITIVE LOGITS
     principles
    0.10
    åħģ许
    0.09
    æĺİç¡®è§Ħå®ļ
    0.09
    åŁºæľ¬åİŁåĪĻ
    0.09
    æĺİç¡®è¦ģæ±Ĥ
    0.09
    è§Ħå®ļ
    0.09
    åħģ许çļĦ
    0.09
    åİŁåĪĻ
    0.09
    çļĦåİŁåĪĻ
    0.08
    缸åħ³è§Ħå®ļ
    0.08
    Activations Density 0.168%

    No Known Activations