© 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. 7851
    Prev
    Next
    INDEX
    Explanations

    called content

    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
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    ales
    -0.08
    horn
    -0.07
    oman
    -0.07
    omas
    -0.07
    ä¸ĢåIJį
    -0.07
    å¾·åĪ©
    -0.07
    vals
    -0.06
    ames
    -0.06
    éĢģèµ°
    -0.06
    POSITIVE LOGITS
    à¹īม
    0.07
    noinspection
    0.07
    è¾½
    0.06
    å°±æĢķ
    0.06
    رÙĬÙħØ©
    0.06
    çĴĥ
    0.06
    GetCurrent
    0.06
    æĬĬåŃ©åŃIJ
    0.06
    anden
    0.06
    说æĺİ
    0.06
    Activations Density 0.001%

    No Known Activations