© 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. 26164
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æŃ»
    -0.08
    çļĦæŃ»
    -0.07
    åħ¬æĬ¥
    -0.07
    xca
    -0.07
    *)_
    -0.07
    awy
    -0.07
    rase
    -0.06
    roz
    -0.06
    ichel
    -0.06
    ibal
    -0.06
    POSITIVE LOGITS
    åŁł
    0.08
    éķ¿æĮīè¯ĨåĪ«äºĮç»´çłģ
    0.07
    çŀ°
    0.07
    æĢİä¹ĪåĬŀ
    0.07
    ÙĤÙĬ
    0.07
    æľ¬é¡µ
    0.07
    cms
    0.06
    ndon
    0.06
    -plugins
    0.06
    æįĮ
    0.06
    Activations Density 0.000%

    No Known Activations