© 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. 27594
    Prev
    Next
    INDEX
    Explanations

    measured values and assessments

    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
    Ø·ÙĦ
    -0.07
    cole
    -0.07
     minor
    -0.07
    mons
    -0.07
    å¤ļæķ°äºº
    -0.06
     Minor
    -0.06
    سÙĪب
    -0.06
    ellone
    -0.06
    pty
    -0.06
    çĽ¸ä¿¡ä½ł
    -0.06
    POSITIVE LOGITS
    å½ĵæŶ
    0.12
     instantaneous
    0.11
     Initially
    0.11
     initially
    0.11
    å½ĵæŶçļĦ
    0.11
    åĪĿæľŁçļĦ
    0.11
    å½ĵæľŁ
    0.11
    åĪĿå§ĭ
    0.11
     contempor
    0.11
    during
    0.11
    Activations Density 0.289%

    No Known Activations