© 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. 21279
    Prev
    Next
    INDEX
    Explanations

    also followed by other words

    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
    jenigen
    -0.11
    ãģĹãģ£ãģĭãĤĬ
    -0.09
    à¸Ļà¹īำ
    -0.09
    å¤ļãģĦ
    -0.08
    er
    -0.08
     ê·¸ëŀĺëıĦ
    -0.08
    raries
    -0.08
    ters
    -0.08
    ious
    -0.07
    edly
    -0.07
    POSITIVE LOGITS
    ation
    0.11
    Ø©
    0.10
    ledes
    0.10
    itecture
    0.09
    entifier
    0.09
    entication
    0.09
    तर
    0.08
    een
    0.08
    ड़
    0.08
     ë¶Ī구íķĺê³ł
    0.08
    Activations Density 0.090%

    No Known Activations