© 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. 60227
    Prev
    Next
    INDEX
    Explanations

    relate to

    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
    orst
    -0.08
    æĥ³å¾ĹåĪ°
    -0.08
    åIJijéĺ³
    -0.08
    istische
    -0.07
    åįĩåĪ°
    -0.07
    trica
    -0.07
    åįĩèĩ³
    -0.07
    keh
    -0.07
    ç¡®ä¿Ŀ
    -0.06
    å¯Ĩå¯Ĩ
    -0.06
    POSITIVE LOGITS
     concerne
    0.08
    æĬĢæľ¯é¢ĨåŁŁ
    0.08
    å¾ģ
    0.07
    主è¦ģä»İäºĭ
    0.07
    fields
    0.07
    çĮĽè¿Ľ
    0.07
    idle
    0.07
     concerned
    0.07
    itzer
    0.06
    为人们
    0.06
    Activations Density 0.880%

    No Known Activations