© 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. 51675
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ane
    -0.08
    åįİåĽ¾
    -0.07
    éĥ½ä¸įéĶĻ
    -0.07
    anes
    -0.07
    åĩ¤
    -0.07
    glieder
    -0.06
    itel
    -0.06
    igel
    -0.06
     gros
    -0.06
    ä¼ĺ
    -0.06
    POSITIVE LOGITS
    å±±ä¸ĭ
    0.08
    åĨįä»İ
    0.07
    æķ²
    0.07
    asl
    0.07
    Ñħла
    0.07
    indsight
    0.07
    jam
    0.07
    èĴ¸èĴ¸
    0.07
    [__
    0.07
    ((__
    0.07
    Activations Density 0.000%

    No Known Activations