© 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. 46911
    Prev
    Next
    INDEX
    Explanations

    ID declares drought

    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
    기ëıĦ
    -0.07
    èĢ½
    -0.07
    ava
    -0.07
    orf
    -0.06
    ddf
    -0.06
    çĴ
    -0.06
    aug
    -0.06
    åıijæĮ¥
    -0.06
    umbo
    -0.06
    ank
    -0.06
    POSITIVE LOGITS
     arbitrary
    0.08
    欲
    0.07
    elize
    0.07
     lust
    0.07
     surv
    0.07
    zte
    0.07
    èĮ¬
    0.07
    åħ¨éĿ¢è´¯å½»èIJ½å®ŀ
    0.07
    elsius
    0.07
    noinspection
    0.07
    Activations Density 0.009%

    No Known Activations