© 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. 45890
    Prev
    Next
    INDEX
    Explanations

    you who are

    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
    mit
    -0.08
    vertime
    -0.07
    ilogue
    -0.07
     hopefully
    -0.07
    komp
    -0.07
    emat
    -0.07
     Neutral
    -0.07
    Ø£ÙħÙĦ
    -0.07
    agus
    -0.07
     arqu
    -0.07
    POSITIVE LOGITS
    ä¸įçŁ¥éģĵæĢİä¹Ī
    0.07
    åĪĨä¸įæ¸ħ
    0.07
    Payload
    0.07
     misunderstanding
    0.07
    endorf
    0.07
    çľĭä¸įè§ģ
    0.07
    çIJĨ解
    0.06
    误解
    0.06
    æ±łä¸Ń
    0.06
    æ··æ·Ĩ
    0.06
    Activations Density 0.002%

    No Known Activations