© 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. 17408
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming constructs

    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
    habi
    -0.08
    íݸ
    -0.08
    doa
    -0.08
     بÙĨا
    -0.07
    ppe
    -0.07
    maz
    -0.07
    rete
    -0.07
    omma
    -0.07
    æīĭåı¯
    -0.07
    porte
    -0.07
    POSITIVE LOGITS
    åIJĮåľ¨
    0.06
    åijĬ
    0.06
    jenigen
    0.06
    çļĻ
    0.06
     Fault
    0.06
    è¶Ĭèµ°è¶Ĭ
    0.06
    elif
    0.06
    Fault
    0.06
     rum
    0.06
    urtles
    0.06
    Activations Density 0.002%

    No Known Activations