© 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. 7379
    Prev
    Next
    INDEX
    Explanations

    increase or decrease due to factors

    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
    åĪĿè¡·
    -0.07
    omu
    -0.07
    ëĵ¬
    -0.07
    rever
    -0.07
    erber
    -0.07
     tipped
    -0.07
    ä½ľæ³ķ
    -0.07
    å½ĵå±ŀ
    -0.07
    omba
    -0.07
    erchant
    -0.07
    POSITIVE LOGITS
    åĪĨ解
    0.11
     contributions
    0.10
    è´¡çĮ®
    0.10
     decomposition
    0.10
    çļĦåĽłç´ł
    0.10
     contribution
    0.09
     contributi
    0.09
     factors
    0.09
     Decom
    0.09
     components
    0.09
    Activations Density 0.279%

    No Known Activations