© 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. 63588
    Prev
    Next
    INDEX
    Explanations

    somehow uncertain outcome

    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
    jsp
    -0.08
    mium
    -0.08
    ê·Ģ
    -0.08
    udit
    -0.08
    castle
    -0.08
    boo
    -0.08
     kemungkinan
    -0.08
    åī¯æľ¬
    -0.08
    æĺ¾çĦ¶æĺ¯
    -0.08
    áb
    -0.08
    POSITIVE LOGITS
    s
    0.08
     váºŃy
    0.07
    ly
    0.07
    ingatkan
    0.07
    (sh
    0.07
     halnya
    0.07
     only
    0.07
    LY
    0.07
    ìĶ©
    0.07
    ا
    0.06
    Activations Density 0.005%

    No Known Activations