© 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. 13629
    Prev
    Next
    INDEX
    Explanations

    lists of numbers 1, 2, 3,

    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
     ~>
    -0.09
    åĨįæİ¥åĨį
    -0.08
     Heim
    -0.08
    Intl
    -0.08
    ignon
    -0.08
    äºĮ人çļĦ
    -0.08
    italia
    -0.08
    à¸Ļิà¹Īà¸ĩ
    -0.08
    大åħ¸
    -0.08
    è¿Ļ两款
    -0.08
    POSITIVE LOGITS
    ...,
    0.07
     until
    0.06
    на
    0.06
    æ·±åħ¥
    0.06
    adore
    0.06
    ulina
    0.06
    اÙħ
    0.06
    até
    0.06
    atoren
    0.05
    ayah
    0.05
    Activations Density 0.007%

    No Known Activations