© 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. 20009
    Prev
    Next
    INDEX
    Explanations

    'S' or 'by' followed by various words

    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
    ש×IJ
    -0.07
    åijĨ
    -0.06
    anela
    -0.06
    ä»»ä½ķåªĴä½ĵ
    -0.06
    åıijå±ķæĶ¹éĿ©
    -0.06
     bl
    -0.06
    .TYPE
    -0.06
     qq
    -0.06
    antom
    -0.06
    åħ¨å±ıæŁ¥çľĭ
    -0.06
    POSITIVE LOGITS
    ä¾Ŀ
    0.10
    æĸ°éĹ®é¢ĺ
    0.08
    azit
    0.08
    ewire
    0.07
    ÑĢÑİ
    0.07
    åŃĺ
    0.07
    ép
    0.07
    åIJĦè¡Į
    0.07
    åı¯ä¾Ŀ
    0.07
    NewItem
    0.07
    Activations Density 0.001%

    No Known Activations