© 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. 32449
    Prev
    Next
    INDEX
    Explanations

    legal and financial resolutions

    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
    æĭħä¿Ŀé£İéĻ©
    -0.08
    asuk
    -0.07
    è¬Ģ
    -0.07
     intentionally
    -0.07
    undler
    -0.07
     Bij
    -0.07
     purposely
    -0.07
     Boh
    -0.07
    伯çī¹
    -0.07
    luv
    -0.07
    POSITIVE LOGITS
    çºłæŃ£
    0.13
    æĶ¹æŃ£
    0.11
    磫æŃ£
    0.11
     restore
    0.11
     restitution
    0.11
     rect
    0.10
    æģ¢å¤į
    0.10
     corrected
    0.10
     restoration
    0.10
     corrective
    0.10
    Activations Density 0.043%

    No Known Activations