© 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. 9717
    Prev
    Next
    INDEX
    Explanations

    key points or tips

    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
    irut
    -0.08
    ffre
    -0.08
    èıģèĭ±
    -0.07
    isit
    -0.07
    ä¸ĢçŃ¹
    -0.07
    åij¢
    -0.07
    åı¯èĥ½å°±
    -0.07
    å¾IJå¾IJ
    -0.07
    ãĥ©ãĥ³ãĤ¯
    -0.07
    æĮīçħ§åĽ½å®¶
    -0.07
    POSITIVE LOGITS
    强è°ĥçļĦæĺ¯
    0.09
    -note
    0.09
    notes
    0.08
    åħ³éĶ®çĤ¹
    0.08
     sottoline
    0.08
    注æĦıçļĦæĺ¯
    0.08
     highlighted
    0.08
    ç©´
    0.07
     points
    0.07
    /key
    0.07
    Activations Density 0.006%

    No Known Activations