© 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. 40159
    Prev
    Next
    INDEX
    Explanations

    react rather than

    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
    æŀĹæµ·
    -0.06
    çĸ¯äºĨ
    -0.06
    лоÑģÑĮ
    -0.06
    ÅĤÄĻ
    -0.06
    ilit
    -0.06
    zia
    -0.06
     Eagles
    -0.06
    ccione
    -0.06
     intern
    -0.06
    è·¨
    -0.06
    POSITIVE LOGITS
    rather
    0.12
     rather
    0.12
    èĢĮä¸įæĺ¯
    0.12
    被åĬ¨
    0.11
    èĢĮéĿŀ
    0.11
     passive
    0.11
     Rather
    0.11
     plutôt
    0.11
     Passive
    0.10
     piuttosto
    0.10
    Activations Density 0.080%

    No Known Activations