© 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. 41102
    Prev
    Next
    INDEX
    Explanations

    contrast to reality

    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
    imente
    -0.08
    uncul
    -0.07
    æĪijåIJ§
    -0.07
    ä¼¼ä¹İä¹Ł
    -0.07
    éĥ½å¸ĮæľĽ
    -0.07
    ضة
    -0.07
    ldr
    -0.07
    lder
    -0.07
     somehow
    -0.07
     Ðļаж
    -0.07
    POSITIVE LOGITS
     actually
    0.15
    å®ŀéĻħä¸Ĭ
    0.14
    åħ¶å®ŀæĺ¯
    0.14
    å®ŀéĻħä¸Ĭæĺ¯
    0.14
    æ®Ĭä¸įçŁ¥
    0.13
    actually
    0.13
    å®ŀåĪĻ
    0.13
    åħ¶å®ŀ
    0.13
    åħ¶å®ŀåľ¨
    0.12
    å®ŁéļĽ
    0.12
    Activations Density 0.362%

    No Known Activations