© 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. 24165
    Prev
    Next
    INDEX
    Explanations

    clear path

    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
    åıĬéĶĢåĶ®
    -0.08
    naire
    -0.08
    orem
    -0.08
    Ń
    -0.08
    rush
    -0.07
    blr
    -0.07
    ®
    -0.07
    ehr
    -0.07
    Unchecked
    -0.07
    igue
    -0.07
    POSITIVE LOGITS
    -cut
    0.12
     rÃłng
    0.12
     اÙĦÙħعاÙĦÙħ
    0.11
    æ¸ħæĻ°çļĦ
    0.10
    æĺİäºĨ
    0.10
     rá»ĩt
    0.10
    -eyed
    0.10
    æ¸ħæĻ°
    0.09
    æĺĵæĩĤ
    0.09
     duid
    0.09
    Activations Density 0.030%

    No Known Activations