© 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. 42073
    Prev
    Next
    INDEX
    Explanations

    command-line operations

    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
    oura
    -0.09
    æĪij社
    -0.09
    æµĴ
    -0.08
    èĻ½çĦ¶ä»ĸ
    -0.08
    åħļç»ĦæĪIJåijĺ
    -0.08
    ahui
    -0.08
    anas
    -0.08
    ãģįãģ«
    -0.07
    [__
    -0.07
    åIJįåī¯
    -0.07
    POSITIVE LOGITS
    å¡ŀå°Ķ
    0.06
    OnError
    0.06
    lette
    0.06
    roupe
    0.06
    terra
    0.06
    eley
    0.06
    æĩĪ
    0.06
    enstein
    0.06
    第ä¸Ģ项
    0.06
    lington
    0.06
    Activations Density 0.030%

    No Known Activations