© 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. 15492
    Prev
    Next
    INDEX
    Explanations

    own, his, clients, death, eligible

    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
    apul
    -0.08
    üst
    -0.08
    FACT
    -0.08
    asures
    -0.08
    ราà¸ĩ
    -0.07
    ä¹ĭé«ĺ
    -0.07
    akaan
    -0.07
    tops
    -0.07
    acea
    -0.07
    å¹´åħ¬åı¸
    -0.07
    POSITIVE LOGITS
     being
    0.07
    izzer
    0.07
     Wo
    0.07
    able
    0.06
    缴å±ŀ
    0.06
    æ§Ľ
    0.06
    ly
    0.06
    ized
    0.06
    åĵij
    0.06
    yai
    0.06
    Activations Density 0.592%

    No Known Activations