© 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. 47870
    Prev
    Next
    INDEX
    Explanations

    allows users/us/for/to

    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
    Ø©
    -0.09
    kel
    -0.08
    .done
    -0.08
    λάÏĩιÏĥ
    -0.08
    oja
    -0.07
    atalog
    -0.07
    mén
    -0.07
    èĤ¯
    -0.07
    sj
    -0.07
    为æ°ij
    -0.07
    POSITIVE LOGITS
    vid
    0.08
     us
    0.07
     quicker
    0.07
    åħ¶åľ¨
    0.07
    ...
    0.07
    çļĦéĥ½æĺ¯
    0.07
    ue
    0.07
    :
    0.07
    iew
    0.07
    ìĦľëĬĶ
    0.07
    Activations Density 0.060%

    No Known Activations