© 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. 45164
    Prev
    Next
    INDEX
    Explanations

    meaning and usage

    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
    etsk
    -0.08
     Lage
    -0.08
    ocha
    -0.07
    æĩĪ
    -0.07
    éģĹæĨ¾
    -0.07
    çIJĨ论ä¸Ĭ
    -0.07
    èĩªåĪ¶
    -0.07
    å¿ĥ仪
    -0.07
    _GAP
    -0.07
    ponsible
    -0.07
    POSITIVE LOGITS
     meanings
    0.12
     usage
    0.12
    çĶ¨æ³ķ
    0.10
     contexts
    0.10
     interpretations
    0.10
    semantic
    0.09
     Usage
    0.09
    å¼ķçĶ³
    0.09
    è¯Ńå¢ĥ
    0.09
    usage
    0.09
    Activations Density 0.069%

    No Known Activations