© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14235
    Prev
    Next
    INDEX
    Explanations

    policy implications or advice

    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
    ness
    -0.13
    abouts
    -0.09
    à¹Ģà¸Ĺียม
    -0.09
    lings
    -0.09
    NESS
    -0.09
    à¹ĥà¸Ī
    -0.08
    ORMAL
    -0.08
    ÑģÑİда
    -0.08
    ights
    -0.08
    OrCreate
    -0.08
    POSITIVE LOGITS
    fully
    0.09
     ìĪĺ립
    0.09
    æĸ¹éĴĪ
    0.09
    æĢ§åľ°
    0.08
    ëĮĢë¡ľ
    0.08
    änder
    0.08
    inally
    0.08
    itical
    0.08
    ally
    0.08
     поводÑĥ
    0.07
    Activations Density 0.016%

    No Known Activations