© 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. 21873
    Prev
    Next
    INDEX
    Explanations

    numeric comparisons

    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
    жек
    -0.09
    embra
    -0.08
    aiss
    -0.08
     неза
    -0.08
    uais
    -0.08
    Recognizer
    -0.08
    르ì§Ģ
    -0.08
    Ïģγ
    -0.08
     ValidationResult
    -0.08
    otify
    -0.08
    POSITIVE LOGITS
     comb
    0.07
    é½
    0.07
     functional
    0.06
     ag
    0.06
     (
    0.06
     compact
    0.06
    èĢ
    0.06
     f
    0.06
    à¹īาว
    0.06
    0.06
    Activations Density 0.028%

    No Known Activations