© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16888
    Prev
    Next
    INDEX
    Explanations

    alternative substitutes placeholders

    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
    æĤĶ
    -0.08
     Sense
    -0.06
    å°±åħĪ
    -0.06
    amani
    -0.06
    ort
    -0.06
    ضÙĬ
    -0.06
     therein
    -0.06
    liest
    -0.06
    arly
    -0.06
    assa
    -0.06
    POSITIVE LOGITS
    æĽ¿ä»£
    0.16
    æĽ¿ä»£åĵģ
    0.15
     substitutes
    0.14
     alternatives
    0.14
     substitute
    0.13
     substituted
    0.13
     replacements
    0.12
     substitution
    0.12
    æĽ¿æį¢
    0.12
     ëĮĢì²´
    0.12
    Activations Density 0.103%

    No Known Activations