© 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. 61597
    Prev
    Next
    INDEX
    Explanations

    figures and illustrations

    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
    erma
    -0.07
    æ²®
    -0.07
    飶
    -0.06
    peed
    -0.06
    z
    -0.06
    wap
    -0.06
    ikel
    -0.06
    å§ĵ
    -0.06
    éģĩ
    -0.06
    ä¸Ĭä¸Ģç¯ĩ
    -0.06
    POSITIVE LOGITS
    ến
    0.08
    WISE
    0.08
    quo
    0.08
    ahren
    0.07
    _pdata
    0.07
    åĸľæ¬¢ä¸Ĭ
    0.07
    âĸ·
    0.07
    blok
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
    OUCH
    0.07
    Activations Density 0.008%

    No Known Activations