© 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. 28809
    Prev
    Next
    INDEX
    Explanations

    half, halves, fraction

    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
    озна
    -0.08
    ÙĬرة
    -0.07
    ahkan
    -0.07
    hdl
    -0.07
    èĩªå·±çļĦ缮æłĩ
    -0.07
    å®ł
    -0.07
    寵
    -0.07
    DT
    -0.07
    aho
    -0.06
     Decision
    -0.06
    POSITIVE LOGITS
    åĢį
    0.11
    åĢįå¢ŀ
    0.09
    åĢįçļĦ
    0.09
    åĬłåĢį
    0.08
     fraction
    0.08
    çĻ¾åĢį
    0.08
    rike
    0.08
    åº
    0.07
    ä¸ĢåįĬ
    0.07
     halves
    0.07
    Activations Density 0.053%

    No Known Activations