© 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. 26482
    Prev
    Next
    INDEX
    Explanations

    dB, Gain, Inventory, difference

    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
     صاØŃ
    -0.08
    å¿ħ须注æĺİ
    -0.08
    çªģçĦ¶éĹ´
    -0.08
    lamour
    -0.07
    çĻ»å½ķåIJİæŁ¥çľĭ
    -0.07
    _REPLACE
    -0.07
    lobals
    -0.07
    ÙħاÙĭ
    -0.07
    åĭ¤æģ³
    -0.07
    æĤį
    -0.07
    POSITIVE LOGITS
    wali
    0.07
    æݸ
    0.07
    空
    0.06
     preservation
    0.06
    解
    0.06
    _creation
    0.06
    kp
    0.06
    нÑĮ
    0.06
    符åIJĪ
    0.06
    ound
    0.06
    Activations Density 0.020%

    No Known Activations