© 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. 15057
    Prev
    Next
    INDEX
    Explanations

    appraisal, legibility, mapping, schema, test, intensity

    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
    inas
    -0.08
    arro
    -0.08
    ijen
    -0.08
    anzas
    -0.07
    itol
    -0.07
    个头
    -0.06
    ipeg
    -0.06
    çħĮ
    -0.06
     Luna
    -0.06
     settled
    -0.06
    POSITIVE LOGITS
    æºĸ
    0.08
    ickl
    0.08
    éĹ²æļĩ
    0.07
    æ¸
    0.07
    æª
    0.07
    ubin
    0.07
    attel
    0.07
    белÑĮ
    0.07
    uegos
    0.06
    è£
    0.06
    Activations Density 0.179%

    No Known Activations