© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63809
    Prev
    Next
    INDEX
    Explanations

    SQL FROM clause

    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
    abu
    -0.07
    ape
    -0.07
    ä¸īæĽ´
    -0.07
    веÑģ
    -0.07
    è»Ĵ
    -0.07
    gov
    -0.06
    è¶ĬãģĹ
    -0.06
    ollo
    -0.06
    å¤ļæķ°
    -0.06
    @m
    -0.06
    POSITIVE LOGITS
    åħ¶ä¸Ń
    0.08
    WHERE
    0.08
    æ
    0.07
    _where
    0.07
     WHERE
    0.07
    baka
    0.06
    å¸ĥ
    0.06
    åħ¶ä¸Ń以
    0.06
    ä½įäºİ
    0.06
    åı¦
    0.06
    Activations Density 0.079%

    No Known Activations