© 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. 56865
    Prev
    Next
    INDEX
    Explanations

    localhost: or /

    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
    ocken
    -0.07
    è´µçļĦ
    -0.07
    eer
    -0.06
     stag
    -0.06
    _NEG
    -0.06
     transl
    -0.06
    å±ħ家éļĶ离
    -0.06
    ä¸ºåĽ½
    -0.06
    æīĢæľª
    -0.06
    åįĬçĤ¹
    -0.06
    POSITIVE LOGITS
     ç§ģ
    0.08
    -errors
    0.07
    _STANDARD
    0.07
    _gateway
    0.07
    丹
    0.07
    änen
    0.07
    aston
    0.07
    à¸Ńุ
    0.07
    ahi
    0.07
    -plugins
    0.07
    Activations Density 0.026%

    No Known Activations