© 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. 49337
    Prev
    Next
    INDEX
    Explanations

    enough room for

    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
    efs
    -0.08
    주ê°Ħ
    -0.07
    åĬŁçĶ¨
    -0.07
    urgi
    -0.07
    好åĥı
    -0.07
    èĩ´åĬĽäºİæīĵéĢł
    -0.07
    çµ±
    -0.07
    tifs
    -0.07
    orea
    -0.07
    ebin
    -0.07
    POSITIVE LOGITS
     adequately
    0.11
    æīĢéľĢçļĦ
    0.10
    æīĢéľĢ
    0.09
     comfortably
    0.09
    æĽ´ä½ķåĨµ
    0.09
    è¶³å¤ŁäºĨ
    0.09
    ä½ķåĨµ
    0.09
    éľĢè¦ģçļĦ
    0.08
    è¶³å¤Ł
    0.08
     ÑħваÑĤиÑĤ
    0.08
    Activations Density 0.136%

    No Known Activations