© 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. 11533
    Prev
    Next
    INDEX
    Explanations

    geometric configurations or groupings

    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
    ibar
    -0.07
    æį¢è¨Ģä¹ĭ
    -0.07
     altrett
    -0.06
    æıĴ
    -0.06
     NotImplementedError
    -0.06
    ofil
    -0.06
    UE
    -0.06
    unto
    -0.06
    æ¤į
    -0.06
    æľªå®Į
    -0.06
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.08
    omat
    0.08
    wit
    0.08
    errick
    0.08
    æľĢä½³çŃĶæ¡Ī
    0.07
     напÑĢимеÑĢ
    0.07
    напÑĢимеÑĢ
    0.07
     nghá»ĭch
    0.07
     Indust
    0.07
    诸å¦Ĥ
    0.07
    Activations Density 0.013%

    No Known Activations