© 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. 8689
    Prev
    Next
    INDEX
    Explanations

    mathematical questions

    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
    ä¿¡æģ¯çĶ±
    -0.09
    ÏģεÏį
    -0.08
    à¸ģะ
    -0.08
    äºīä¼ĺ
    -0.08
    hev
    -0.08
    kaar
    -0.08
    æµģçļĦ
    -0.08
    bygg
    -0.07
    /.
    -0.07
    ISTR
    -0.07
    POSITIVE LOGITS
    uah
    0.07
    åħ·ä½ĵ
    0.06
     realised
    0.06
    amel
    0.06
    çŁ³çģ°
    0.06
    çĶ°
    0.06
    ä¸įæĶ¾
    0.06
    rm
    0.06
    åIJĪçIJĨ
    0.06
    acl
    0.06
    Activations Density 0.001%

    No Known Activations