© 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. 42637
    Prev
    Next
    INDEX
    Explanations

    variable name or function argument

    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
    ummings
    -0.07
    åĩ«
    -0.07
    åħ¸åŀĭ
    -0.07
    æĮīçħ§è§Ħå®ļ
    -0.07
    åıĸåħ¶
    -0.07
    è®©æĽ´å¤ļ读èĢħ
    -0.07
    Unchecked
    -0.07
    allery
    -0.07
    ä¸į失
    -0.07
    Playable
    -0.07
    POSITIVE LOGITS
    bund
    0.08
    èĢĮå·²
    0.07
     shorter
    0.07
     sometimes
    0.07
     occasional
    0.07
    é¡¹çĽ®åIJį称
    0.07
     bund
    0.07
     introductory
    0.07
    åĶıåĺĺ
    0.06
     repetitions
    0.06
    Activations Density 0.001%

    No Known Activations