© 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. 48599
    Prev
    Next
    INDEX
    Explanations

    license

    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
    ادÙħ
    -0.08
    ince
    -0.08
    apan
    -0.08
    -0.08
    agram
    -0.08
    avais
    -0.07
    .PNG
    -0.07
    arme
    -0.07
    igram
    -0.07
    ãĤ¸ãĥ¼
    -0.07
    POSITIVE LOGITS
    éĹŃ
    0.07
    quate
    0.07
    ä»¥æĽ´åĬł
    0.06
    è·Łè´´
    0.06
    å¼±çĶµ
    0.06
    èĩªéĹŃ
    0.06
    åĮ¹åħĭ
    0.06
    çĽ²
    0.06
     Amid
    0.06
    es
    0.06
    Activations Density 0.010%

    No Known Activations