© 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. 45156
    Prev
    Next
    INDEX
    Explanations

    specific term types

    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
    phin
    -0.07
    åħ³äºİè¿Ľä¸ĢæŃ¥
    -0.07
    çĥ¤æ¼Ĩ
    -0.07
    ä¹ĭ以
    -0.07
    çİ©çİ©
    -0.06
    angk
    -0.06
    éĩijå±±
    -0.06
    RequestMethod
    -0.06
    (Keys
    -0.06
    oins
    -0.06
    POSITIVE LOGITS
     ане
    0.08
    ime
    0.07
    -focused
    0.07
    ahn
    0.07
    ified
    0.07
    é¹ĥ
    0.07
    -based
    0.07
    好å¥ĩå¿ĥ
    0.06
    coop
    0.06
    iri
    0.06
    Activations Density 0.158%

    No Known Activations