© 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. 17295
    Prev
    Next
    INDEX
    Explanations

    following texts

    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
    eger
    -0.08
    åĽłæѤ
    -0.07
     tslint
    -0.07
    meen
    -0.06
    enth
    -0.06
    âľħ
    -0.06
    éĩijæŃ£
    -0.06
    寮
    -0.06
    ény
    -0.06
    upes
    -0.06
    POSITIVE LOGITS
    oader
    0.07
    åħĪä»İ
    0.07
    starting
    0.07
    omu
    0.07
    cken
    0.07
     delibera
    0.07
    è¿ĩåįĬ
    0.07
     starting
    0.07
    æŃ£å¼ıå¼Ģå§ĭ
    0.07
    Starting
    0.07
    Activations Density 0.001%

    No Known Activations