© 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. 8038
    Prev
    Next
    INDEX
    Explanations

    order of approximation

    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
    zerw
    -0.09
    å¤§åľ£
    -0.08
    odox
    -0.08
    zÄĻ
    -0.08
    享
    -0.08
    æ¯ıéļĶ
    -0.08
    archs
    -0.08
    adeiras
    -0.08
    apo
    -0.08
    è¡·
    -0.07
    POSITIVE LOGITS
     terms
    0.07
    夷
    0.07
     contributions
    0.07
    çĹħ
    0.06
    TERM
    0.06
     contribution
    0.06
    ij
    0.06
    æ·¹
    0.06
     Terms
    0.06
    åĨ
    0.06
    Activations Density 0.002%

    No Known Activations