© 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. 18225
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with assignment

    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
    èĩªå·±
    -0.15
    quoi
    -0.14
    odore
    -0.12
    etheless
    -0.12
    atre
    -0.10
    èĩªå·±æ²¡æľī
    -0.10
    èĩªå·±è¢«
    -0.10
    ments
    -0.09
    bsites
    -0.09
    efois
    -0.09
    POSITIVE LOGITS
    0.08
    ·
    0.08
    partment
    0.08
    CREMENT
    0.07
     ($("#
    0.07
    cpt
    0.07
    ToMany
    0.07
    rific
    0.07
    ervas
    0.07
    stile
    0.07
    Activations Density 0.463%

    No Known Activations