© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48868
    Prev
    Next
    INDEX
    Explanations

    Jackson, Mason, Tanner, land, inden

    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
    rippling
    -0.07
    p
    -0.07
    äºĭ
    -0.06
    estar
    -0.06
    å¤§ä½ľ
    -0.06
    rebs
    -0.06
    Boom
    -0.06
    åıªè§ģ
    -0.06
    s
    -0.06
    c
    -0.06
    POSITIVE LOGITS
     ân
    0.08
    èī²åĪĹ
    0.08
    yku
    0.08
    дне
    0.08
    ëĿ¼ìĿ´
    0.07
    mener
    0.07
     INTROD
    0.07
    мага
    0.07
    ienia
    0.07
    beer
    0.07
    Activations Density 1.464%

    No Known Activations