© 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. 23436
    Prev
    Next
    INDEX
    Explanations

    months and headers

    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
    Ø©
    -0.17
    ами
    -0.11
    een
    -0.10
    ovich
    -0.09
    eor
    -0.09
    º
    -0.09
    eon
    -0.09
    à¸ģารà¸ĵà¹Į
    -0.09
    eper
    -0.09
    nai
    -0.09
    POSITIVE LOGITS
    er
    0.08
    ëį°ìļĶ
    0.07
    ra
    0.07
    ãĥ³
    0.07
    i
    0.07
    iable
    0.07
    “
    0.06
    ìį¨
    0.06
    ers
    0.06
    ri
    0.06
    Activations Density 0.028%

    No Known Activations