© 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. 17689
    Prev
    Next
    INDEX
    Explanations

    questions asking for calculations

    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
    çł¥
    -0.08
    spm
    -0.08
    ymar
    -0.08
    าà¸ģลาà¸ĩ
    -0.07
    endale
    -0.07
    edora
    -0.07
    é¢ijé¢ij
    -0.07
    çĶŁæ´»ä¼ļ
    -0.07
    ebas
    -0.07
    (PR
    -0.07
    POSITIVE LOGITS
    scape
    0.07
    âĢ
    0.07
    elsey
    0.07
    âĢļ
    0.06
    ights
    0.06
     pars
    0.06
    bauer
    0.06
    F
    0.06
    bury
    0.06
    ight
    0.06
    Activations Density 0.003%

    No Known Activations