© 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. 48617
    Prev
    Next
    INDEX
    Explanations

    Z, ZW, ZQ, ZI, ZA

    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
    æŃ¢åĴ³
    -0.08
    ucci
    -0.08
    chez
    -0.08
    IgnoreCase
    -0.08
    åĨįèĢħ
    -0.08
    ç»ĿæĬĢ
    -0.07
    uzzi
    -0.07
    ÑģÑĮ
    -0.07
    蹤
    -0.07
    yles
    -0.07
    POSITIVE LOGITS
    ephy
    0.19
    ÅĻejmÄĽ
    0.16
    ombies
    0.15
    ebra
    0.15
    imbabwe
    0.15
    abbix
    0.15
    hejiang
    0.13
    adrž
    0.13
    ephir
    0.13
    odiac
    0.13
    Activations Density 0.524%

    No Known Activations