© 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. 29179
    Prev
    Next
    INDEX
    Explanations

    both enzymesHygienePiercingImpresariocan beElsewhere

    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
     either
    -0.07
    fes
    -0.07
     Either
    -0.07
    either
    -0.06
    è¦ģä¹Ī
    -0.06
    ÑģÑĤÑĥпиÑĤÑĮ
    -0.06
    -0.06
    æģ°å¥½
    -0.06
    å¥ł
    -0.06
     somehow
    -0.06
    POSITIVE LOGITS
    åľ¨æµ·å¤ĸ
    0.09
    ahu
    0.09
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    0.08
    åĽ½å®¶åĴĮåľ°åĮº
    0.08
    ä¸İåħ¶å®ĥ
    0.08
    ä¹Łç»ı常
    0.08
    angan
    0.08
    æĽ´å¤ļåħ³äºİ
    0.08
    åĴĮåħ¶å®ĥ
    0.08
    omencl
    0.08
    Activations Density 0.005%

    No Known Activations