© 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. 12178
    Prev
    Next
    INDEX
    Explanations

    questions and polls

    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
    ELTS
    -0.09
    airy
    -0.08
    建议书
    -0.08
    ersist
    -0.08
    个人页
    -0.07
     Kabar
    -0.07
    ẹp
    -0.07
    taat
    -0.07
    åħ¬ç§ģ
    -0.07
    ieties
    -0.07
    POSITIVE LOGITS
    poll
    0.08
    éĢīåĩº
    0.08
    æĹ¨åľ¨
    0.07
    å¤ļéĢī
    0.07
    éĹ®ä½ł
    0.07
    çŃł
    0.07
    izz
    0.07
     selecting
    0.07
    éĹ®åĮ»çĶŁ
    0.07
    éĹ®
    0.07
    Activations Density 0.008%

    No Known Activations