© 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. 57472
    Prev
    Next
    INDEX
    Explanations

    dipole

    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
    缸è¾ħ缸æĪIJ
    -0.09
    俱ä¹IJéĥ¨
    -0.09
    peed
    -0.09
    nable
    -0.08
    eves
    -0.08
    desk
    -0.08
    cape
    -0.08
    tings
    -0.08
    两åѦä¸Ģåģļ
    -0.08
    ëĭ¤ëĬĶ
    -0.08
    POSITIVE LOGITS
    /qu
    0.08
    -like
    0.08
    i
    0.08
    orest
    0.07
    ity
    0.07
    fect
    0.07
    lectic
    0.07
    åŃIJä¾Ľ
    0.07
    oid
    0.07
    iel
    0.07
    Activations Density 0.010%

    No Known Activations