© 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. 25596
    Prev
    Next
    INDEX
    Explanations

    lasting tribute

    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
    losion
    -0.06
    kola
    -0.06
     kinds
    -0.06
    <![
    -0.06
     Konz
    -0.06
    åħīè¾ī
    -0.06
    çļĦéĤ£äºĽ
    -0.06
    å¥Ĺ
    -0.06
    æĽ°
    -0.06
    æĢ§æĪĸ
    -0.06
    POSITIVE LOGITS
    衬衣
    0.07
    å°´
    0.07
    æįĹ
    0.07
    imbang
    0.07
    assoc
    0.07
    FLT
    0.07
    ACES
    0.07
    TTY
    0.07
    adier
    0.07
    人å¿ĥ弦
    0.07
    Activations Density 0.047%

    No Known Activations