© 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. 50007
    Prev
    Next
    INDEX
    Explanations

    validation, calibration, adjustment, testing

    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
     forged
    -0.07
    WISE
    -0.06
    labs
    -0.06
    æĦŁ
    -0.06
     scanned
    -0.06
    è§Ĩå¯Ł
    -0.06
    ä¼ģä¸ļ认è¯ģ
    -0.06
     studied
    -0.06
    icense
    -0.06
    ickle
    -0.06
    POSITIVE LOGITS
    åĪ°æľī
    0.09
    çļĦ缮çļĦ
    0.09
    æĮīçħ§è§Ħå®ļ
    0.09
    æľ¬çĿĢ
    0.09
    缮çļĦåľ¨äºİ
    0.09
    å®Įæ¯ķåIJİ
    0.08
    çļĦéĩįçĤ¹
    0.08
    åĨħ容åĮħæĭ¬
    0.08
    åĿļæĮģä¸įæĩĪ
    0.08
    ä¹ĭ缮çļĦ
    0.08
    Activations Density 0.035%

    No Known Activations