© 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. 11090
    Prev
    Next
    INDEX
    Explanations

    classification concepts

    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
    ç¥ŀå±±
    -0.08
    kler
    -0.08
    -thumb
    -0.08
    atsu
    -0.08
    quential
    -0.07
    paced
    -0.07
    /boot
    -0.07
    antik
    -0.07
     Shelf
    -0.07
    å½ķ
    -0.07
    POSITIVE LOGITS
     Classification
    0.10
     classification
    0.10
     classify
    0.10
     classified
    0.09
    Classification
    0.08
    åĪĨç±»
    0.08
    classification
    0.07
    classify
    0.07
     classifications
    0.07
    onis
    0.07
    Activations Density 0.007%

    No Known Activations