© 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. 12341
    Prev
    Next
    INDEX
    Explanations

    alternatives or conjunctions

    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
    å¤ĩæ¡Īåı·
    -0.06
    è
    -0.06
     bud
    -0.06
    ä¸Ģè¦ģ
    -0.06
    以åĪ©
    -0.06
    ç¦
    -0.06
    /-
    -0.06
    ×ķ×ķ
    -0.06
    yu
    -0.06
    ä¸įæĺ¯åľ¨
    -0.06
    POSITIVE LOGITS
    DataContext
    0.08
    éĥİ
    0.08
    lden
    0.07
    BBBB
    0.07
    zas
    0.07
    åħ¨çĦ¶
    0.07
    ffy
    0.07
    ieties
    0.07
    ssl
    0.07
    å¤§æľ¬
    0.07
    Activations Density 0.624%

    No Known Activations