© 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. 40828
    Prev
    Next
    INDEX
    Explanations

    extract, export, hide

    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
    imps
    -0.07
    äºĨä¸ĢåĪĩ
    -0.07
    IOUS
    -0.07
    ious
    -0.07
    æľīå½¢
    -0.06
    åĩºå¸ŃäºĨ
    -0.06
    kis
    -0.06
    posix
    -0.06
    æ´½
    -0.06
    (loss
    -0.06
    POSITIVE LOGITS
    åİŁæĸĩåĩºå¤Ħ
    0.08
    æĪijæĥ³
    0.08
    .ini
    0.08
    èĩªå®ļä¹ī
    0.08
    vert
    0.08
    takt
    0.07
    NER
    0.07
    oop
    0.07
    æľ¬æĸĩçĶ±
    0.07
    asily
    0.07
    Activations Density 3.709%

    No Known Activations