© 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. 24603
    Prev
    Next
    INDEX
    Explanations

    variable or dynamic quantities

    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
     revamped
    -0.09
    æŁij
    -0.08
    æŀľçĦ¶
    -0.08
    _assert
    -0.08
    æĶ¾å¿ĥ
    -0.07
    γα
    -0.07
    约æľī
    -0.07
    åĬłæĸ¯
    -0.07
    æĺĵè´Ń
    -0.07
    íĥķ
    -0.07
    POSITIVE LOGITS
     arbitrary
    0.12
    åĽºå®ļçļĦ
    0.11
     arbitrarily
    0.11
     fixed
    0.10
    éļıæĦı
    0.10
    éļı
    0.10
    åĽºå®ļ
    0.09
     randomly
    0.09
     independently
    0.09
    èĩªçĶ±éĢīæĭ©
    0.09
    Activations Density 0.064%

    No Known Activations