© 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. 18097
    Prev
    Next
    INDEX
    Explanations

    required by

    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
    ä¸įå¹²
    -0.07
    vero
    -0.06
    说åIJ§
    -0.06
    æķĻå¸Īè¦ģ
    -0.06
    çijŀå®ī
    -0.06
     determination
    -0.06
    å¾ħåĪ°
    -0.06
    åĸ¶
    -0.06
    ÑĤей
    -0.06
    ponde
    -0.06
    POSITIVE LOGITS
    ecker
    0.09
    ãģªãģį
    0.08
    丹丹
    0.08
    jene
    0.08
    utie
    0.08
    ç«ĭåĬŁ
    0.07
    ì§Ģìĸ´
    0.07
    ä¿±è¿Ľ
    0.07
    kken
    0.07
    ='',
    0.07
    Activations Density 0.613%

    No Known Activations