© 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. 51039
    Prev
    Next
    INDEX
    Explanations

    effective dose

    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
     Kemp
    -0.07
    trup
    -0.07
    -sur
    -0.07
    æľīæĦŁ
    -0.07
    ä¸ĥåįģ
    -0.07
    üren
    -0.07
    atings
    -0.07
    amins
    -0.07
     *))
    -0.07
    çī¹æĸ°
    -0.06
    POSITIVE LOGITS
    éļıä¹ĭ
    0.10
    ĸ
    0.09
     thereof
    0.09
     daraus
    0.08
     accordingly
    0.08
    ä¹Łéļıä¹ĭ
    0.08
     consequently
    0.07
    å¹
    0.07
    继
    0.07
    欢
    0.07
    Activations Density 0.185%

    No Known Activations