© 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. 58093
    Prev
    Next
    INDEX
    Explanations

    math 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
    abay
    -0.06
    —
    -0.06
    åİĨéĻ©
    -0.06
    yled
    -0.06
    æī°
    -0.06
     *
    -0.05
    就该
    -0.05
    临åħ¶
    -0.05
    abled
    -0.05
    ,
    -0.05
    POSITIVE LOGITS
    éz
    0.10
     inoltre
    0.09
    ."),
    0.08
     âĤ¬*
    0.08
     ës
    0.08
    cÃŃ
    0.08
    oja
    0.08
    âĹĩâĹĨ
    0.08
    bÃŃ
    0.08
    ä¸įè¦ģåľ¨
    0.08
    Activations Density 0.129%

    No Known Activations