© 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. 56231
    Prev
    Next
    INDEX
    Explanations

    objects and their attributes

    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
    ild
    -0.07
    è¿ĺæĺ¯æĮº
    -0.06
    é¢Ĩ导åıĬ
    -0.06
    ä¸ĬåĬł
    -0.06
    Ñıм
    -0.06
     vibrating
    -0.06
    uhe
    -0.06
    éĥ½èĥ½çľĭåĪ°
    -0.06
     Å¡i
    -0.06
    zah
    -0.06
    POSITIVE LOGITS
    ToPoint
    0.08
    èģĶç³»åķĨ家
    0.08
    ä¸ĩä¸ĩ
    0.08
    pal
    0.07
    aniei
    0.07
    adwal
    0.07
    HLT
    0.06
    adm
    0.06
    secs
    0.06
    aner
    0.06
    Activations Density 0.002%

    No Known Activations