© 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. 34320
    Prev
    Next
    INDEX
    Explanations

    deemed selectable, significant, defective

    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
    enda
    -0.08
    pite
    -0.07
    ENSE
    -0.07
    çļĦç¾İ好
    -0.07
    ahan
    -0.07
    好èĩªå·±çļĦ
    -0.07
    ampa
    -0.06
    aff
    -0.06
    pector
    -0.06
    arters
    -0.06
    POSITIVE LOGITS
    theless
    0.12
    ÙĨ
    0.11
    è¯ļåĭ¿æī°
    0.11
    éļ¾äºĭ
    0.09
    ä¹ĭä½ľ
    0.09
    åīįè¿°
    0.09
    ãģªãĤīãģļ
    0.08
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.08
    ÙĦز
    0.08
    ä½ķåľ°
    0.08
    Activations Density 0.002%

    No Known Activations