© 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. 20441
    Prev
    Next
    INDEX
    Explanations

    Ricci curvature, zone militarily, convex hull of points

    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
    èĤ¯å®ļè¦ģ
    -0.08
    ÑģÑĤв
    -0.08
    eneg
    -0.07
    ì£Ħ
    -0.07
    åIJĦ级åIJĦç±»
    -0.07
     lit
    -0.07
    æĿŁæīĭ
    -0.07
    تب
    -0.07
    enen
    -0.07
    è¾ķ
    -0.07
    POSITIVE LOGITS
     except
    0.08
     Except
    0.08
     om
    0.08
    except
    0.07
    eth
    0.07
    andal
    0.07
    inks
    0.07
    Except
    0.07
    iente
    0.06
    ocat
    0.06
    Activations Density 0.014%

    No Known Activations