© 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. 48756
    Prev
    Next
    INDEX
    Explanations

    preparation method

    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
    éĩįéĩįçļĦ
    -0.09
    ulle
    -0.09
    бби
    -0.08
    |array
    -0.08
    oppi
    -0.08
    ennon
    -0.08
     nhau
    -0.08
    reo
    -0.08
    ycz
    -0.08
    ammers
    -0.08
    POSITIVE LOGITS
    åĩºæĿ¥çļĦ
    0.08
    åĴĮ使çĶ¨
    0.08
    OrUpdate
    0.07
    ighton
    0.07
    åĩºæĿ¥
    0.07
    ares
    0.07
    ű
    0.07
    igny
    0.07
    åĪĿè¡·
    0.07
    StackTrace
    0.06
    Activations Density 0.046%

    No Known Activations