© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23275
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    uÃŃ
    -0.08
    ä¸įåłª
    -0.08
    chini
    -0.08
    èĻ½çĦ¶åľ¨
    -0.08
    ë²
    -0.08
    loo
    -0.08
    estr
    -0.08
    ujur
    -0.07
    ä¸įåħī
    -0.07
    otland
    -0.07
    POSITIVE LOGITS
     also
    0.06
    anic
    0.06
     hint
    0.06
    å°Ĩå®ĥ们
    0.06
    ä¹ŁæĬĬ
    0.06
    enton
    0.06
    å®ĥè¿ĺ
    0.06
     H
    0.06
     uk
    0.06
    对éĤ£äºĽ
    0.06
    Activations Density 0.669%

    No Known Activations