© 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. 29497
    Prev
    Next
    INDEX
    Explanations

    for the purposes of

    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
    ×Ļרת
    -0.07
    edia
    -0.07
    iamond
    -0.07
    ë¶ĢíĦ°
    -0.07
     demikian
    -0.07
    å¸ĮæľĽå¯¹æĤ¨
    -0.07
    hlas
    -0.07
    Ñħождение
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    ONUS
    -0.06
    POSITIVE LOGITS
     sake
    0.20
     purposes
    0.17
     reasons
    0.14
     Zwecke
    0.13
    bidden
    0.13
    åİŁåĽł
    0.10
     ÙĪÙĦÙĦ
    0.10
     raisons
    0.10
    ç¼ĺæķħ
    0.10
    feit
    0.10
    Activations Density 0.758%

    No Known Activations