© 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. 47368
    Prev
    Next
    INDEX
    Explanations

    abnormalities and dysfunctions

    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
    apo
    -0.08
    ála
    -0.08
    auta
    -0.07
    onden
    -0.07
    ковой
    -0.07
    árs
    -0.07
    _force
    -0.07
     ÑĢождении
    -0.07
    quire
    -0.07
    çĺ¦èĦ¸
    -0.07
    POSITIVE LOGITS
    äºĨçļĦ
    0.09
    Occurred
    0.09
    æĪĸ缺
    0.08
     loạn
    0.08
    åįĥ家
    0.08
    主è¦ģ表çİ°åľ¨
    0.08
    主è¦ģ表çݰ为
    0.08
    /dis
    0.08
    ments
    0.08
    失常
    0.08
    Activations Density 0.164%

    No Known Activations