© 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. 19539
    Prev
    Next
    INDEX
    Explanations

    abstract:

    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
    ame
    -0.07
    anc
    -0.06
    ena
    -0.06
     bus
    -0.06
    å°±æĺ¯æľī
    -0.06
    uckle
    -0.06
    Äįin
    -0.06
    ampling
    -0.06
     fod
    -0.06
    d
    -0.06
    POSITIVE LOGITS
    ieri
    0.09
    istine
    0.08
    âĹ¯
    0.08
     séqu
    0.07
    ldre
    0.07
    ä¸Ģ带
    0.07
    رÙĬØ·
    0.07
    _ENDIAN
    0.07
    ocker
    0.07
    shan
    0.07
    Activations Density 0.009%

    No Known Activations