© 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. 22085
    Prev
    Next
    INDEX
    Explanations

    sorting lambda functions

    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
    å½ĵéĿ¢
    -0.07
    htag
    -0.06
    åĢ©
    -0.06
    alh
    -0.06
    ä¸Ģè´¯
    -0.06
    ew
    -0.06
    geg
    -0.06
    .mongo
    -0.06
    PU
    -0.06
    aggio
    -0.06
    POSITIVE LOGITS
    æѤçĶŁ
    0.10
    çĵ¢
    0.08
    çıĪ
    0.07
    azon
    0.07
     Rooney
    0.07
    gara
    0.07
    èĦ¾æ°Ķ
    0.07
     maupun
    0.06
    è¿ĶåĽŀ缮å½ķ
    0.06
    rs
    0.06
    Activations Density 0.032%

    No Known Activations