© 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. 21581
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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
    éĻ·
    -0.06
    ially
    -0.06
    çĶ¨ä¸Ģ个
    -0.06
    ENA
    -0.06
    ately
    -0.06
     Garc
    -0.06
    è§ģæѤ
    -0.06
    ож
    -0.06
    itel
    -0.06
    ly
    -0.06
    POSITIVE LOGITS
    ä¸īçĶŁ
    0.09
    udson
    0.09
    armo
    0.08
    avana
    0.08
    åı¯æ¢¦
    0.08
     consc
    0.08
    urangan
    0.08
    uida
    0.07
    ryp
    0.07
    AIS
    0.07
    Activations Density 0.004%

    No Known Activations