© 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. 13075
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    æł¹æį®åĽ½å®¶
    -0.08
    ئÙĬÙĨ
    -0.08
    æ¸ħç§Ģ
    -0.08
    èĤ¯å®ļ
    -0.07
    acre
    -0.07
    adia
    -0.07
    ä»ĺãģij
    -0.07
    alsy
    -0.07
    agne
    -0.07
    iece
    -0.07
    POSITIVE LOGITS
    森
    0.07
    å§ľ
    0.07
     wander
    0.07
    èĩ³æѤ
    0.07
    åѤ
    0.06
    æĤ£
    0.06
    =}
    0.06
    lach
    0.06
    enhagen
    0.06
    åı°å¤§
    0.06
    Activations Density 0.009%

    No Known Activations