© 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. 38873
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with m

    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
    ateg
    -0.09
    vand
    -0.08
    atron
    -0.08
    éĩįè¿Ķ
    -0.08
    çĹ©
    -0.08
    -roll
    -0.07
    _dl
    -0.07
    çĺ¦èĦ¸
    -0.07
    asha
    -0.07
    .EventType
    -0.07
    POSITIVE LOGITS
     (?
    0.07
    ErrorException
    0.07
    rave
    0.06
    ï¼Ī
    0.06
     (?)
    0.06
     (
    0.06
    åħ·ä½ĵæĿ¥è¯´
    0.06
    vera
    0.06
    ãĢįï¼Ī
    0.06
    üh
    0.06
    Activations Density 0.003%

    No Known Activations