© 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. 8589
    Prev
    Next
    INDEX
    Explanations

    collision

    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
    ENTI
    -0.08
    ¶
    -0.08
    èļ£
    -0.08
    aml
    -0.08
    psilon
    -0.07
    afil
    -0.07
    dig
    -0.07
    cript
    -0.07
    erge
    -0.07
    erior
    -0.07
    POSITIVE LOGITS
     nhau
    0.10
    aneous
    0.09
    ../
    0.08
    à¸ģัà¸Ļ
    0.08
    æľ¬ç½ijç«Ļ
    0.08
    ingly
    0.08
    à¸ģัà¸Ļà¹Ħà¸Ķà¹ī
    0.08
    aison
    0.08
    åĩºä¸Ģ个
    0.08
    à¸ģัà¸ļ
    0.08
    Activations Density 0.027%

    No Known Activations