© 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. 15979
    Prev
    Next
    INDEX
    Explanations

    round to the nearest

    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
    «
    -0.07
     «
    -0.06
     depth
    -0.06
     pass
    -0.06
    yr
    -0.06
    et
    -0.06
    ()
    -0.06
     ar
    -0.05
     guest
    -0.05
    -
    -0.05
    POSITIVE LOGITS
    elos
    0.08
    ιÏĥÏĦα
    0.08
    bane
    0.08
    hints
    0.08
    XB
    0.08
    Licensed
    0.08
    BigInt
    0.08
    izont
    0.08
    ÙĪÙħØ©
    0.08
    hund
    0.08
    Activations Density 0.001%

    No Known Activations