© 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. 40842
    Prev
    Next
    INDEX
    Explanations

    email or message

    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
    apult
    -0.08
     خار
    -0.07
    HOOK
    -0.07
    ga
    -0.07
     Bol
    -0.07
    adra
    -0.07
    ìĤ°
    -0.06
    åĽºæľīçļĦ
    -0.06
    orta
    -0.06
    ä¸Ģéģį
    -0.06
    POSITIVE LOGITS
    书éĿ¢
    0.08
    ä¸įèĥľ
    0.07
    forme
    0.07
    ãĥķãĤ©ãĥ¼ãĥł
    0.07
    [email
    0.07
     preferably
    0.07
    楷
    0.07
     specifying
    0.07
    yscale
    0.07
     anytime
    0.07
    Activations Density 0.295%

    No Known Activations