© 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. 51537
    Prev
    Next
    INDEX
    Explanations

    also adding further details

    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
    mig
    -0.08
    alas
    -0.08
    estro
    -0.08
    ä¸Ģåıij
    -0.07
    å§ĭç»Ī以
    -0.07
    inggal
    -0.07
    åIJĥå®Į
    -0.07
    ereo
    -0.07
    klen
    -0.07
    stadt
    -0.07
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.08
    åľ¨åĨħ
    0.08
    çļĦè¿ĺæľī
    0.07
    ä¸Ģæł·
    0.07
     turut
    0.07
    èį·
    0.07
    åĨħæľī
    0.06
    åħ¶å®ĥ
    0.06
    Õ¶Õ¥ÖĢ
    0.06
     other
    0.06
    Activations Density 0.189%

    No Known Activations