© 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. 19525
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units/qualifiers

    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
    åĭĥ
    -0.07
    é¢Ĩ
    -0.06
    æ¦Ĥ
    -0.06
     Ø·
    -0.06
    åŃIJæĽ°
    -0.06
    ئÙħ
    -0.06
    çĶ»
    -0.06
    å¤ĩ
    -0.06
    æŀĦæĪIJ
    -0.06
    å¾ĪæĹ©å°±
    -0.06
    POSITIVE LOGITS
    ä¹ĭå¤ļ
    0.09
    <|box_end|>
    0.08
    ä¸Ńè¡Į
    0.08
    ฯ
    0.08
    /-
    0.07
    è¡ĮéĹ´
    0.07
    è¡ħ
    0.07
    ä¸įè¡°
    0.07
    ackers
    0.07
    icot
    0.07
    Activations Density 0.060%

    No Known Activations