© 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. 16642
    Prev
    Next
    INDEX
    Explanations

    P.2d

    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
    acea
    -0.08
    igna
    -0.08
    kea
    -0.08
    éľī
    -0.08
    ubishi
    -0.07
    rophe
    -0.07
    åĪ¶å®ļæľ¬
    -0.07
    arga
    -0.07
    endance
    -0.07
    :last
    -0.07
    POSITIVE LOGITS
    天æĪIJ
    0.08
     J
    0.06
    èIJ½æĪIJ
    0.06
     forces
    0.06
    丧失
    0.06
     nop
    0.06
    forces
    0.06
    ayaan
    0.06
    èݱçī¹
    0.06
    èģĮæĿĥ
    0.06
    Activations Density 0.089%

    No Known Activations