© 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. 60815
    Prev
    Next
    INDEX
    Explanations

    electrical discharge and lightning

    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
    åĬ¨äºĨ
    -0.08
     weights
    -0.08
    活水
    -0.08
     Entrev
    -0.08
    ä¸įåĩı
    -0.08
    adera
    -0.07
    äºĨçĦ¶
    -0.07
     Turtle
    -0.07
    ä¼¼éĶ¦
    -0.07
    sson
    -0.07
    POSITIVE LOGITS
    æĶ¾çĶµ
    0.12
    åĩ»ç©¿
    0.12
    çģ«èĬ±
    0.11
    çĶµæŀģ
    0.09
     lightning
    0.09
     electric
    0.09
     electrodes
    0.08
    大æ°Ķ
    0.08
     electrode
    0.08
     electricity
    0.08
    Activations Density 0.056%

    No Known Activations