© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14326
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences

    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
    é»į
    -0.08
    çĻ¾åº¦çĻ¾ç§ij
    -0.07
    æ¯Ĥ
    -0.07
     Palav
    -0.07
    ervlet
    -0.07
    ä¸Ģæī«
    -0.07
    ashian
    -0.07
    aje
    -0.07
    ieu
    -0.06
    ardu
    -0.06
    POSITIVE LOGITS
    å¸Ń
    0.07
    ãĥ¯ãĤ¤
    0.07
    eras
    0.07
    å¸Į
    0.06
     Sands
    0.06
    εδ
    0.06
    åIJijæľ¬éĻ¢
    0.06
    _HIDE
    0.06
    ä½įçļĦ
    0.06
    actory
    0.06
    Activations Density 0.048%

    No Known Activations