© 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. 19714
    Prev
    Next
    INDEX
    Explanations

    also, additionally, and moreover

    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
    aland
    -0.07
    alone
    -0.07
     enough
    -0.06
    ео
    -0.06
    ny
    -0.06
    纤
    -0.06
    ible
    -0.06
    éĩijé»Ħ
    -0.06
    Allows
    -0.06
    çŃ
    -0.06
    POSITIVE LOGITS
    ×ŀ×ķת
    0.09
    ¶
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ligh
    0.07
    itoris
    0.07
    rase
    0.07
    ê±°
    0.07
    ä¸īæĹł
    0.07
    ucid
    0.07
    è¿ĩ好
    0.07
    Activations Density 0.014%

    No Known Activations