© 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. 9712
    Prev
    Next
    INDEX
    Explanations

    welcome and greetings

    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
    {_
    -0.08
    çŃīçĿĢä½ł
    -0.08
    éĹ®åĮ»çĶŁ
    -0.08
    æķĻä½łå¦Ĥä½ķ
    -0.08
    该åİ¿
    -0.08
     derp
    -0.07
    ordes
    -0.07
    è·ijåİ»
    -0.07
    ?p
    -0.07
    onis
    -0.07
    POSITIVE LOGITS
     today
    0.10
     tonight
    0.10
    ä»Ĭ天çļĦ
    0.10
    æĪij们ä»Ĭ天
    0.09
    ä½łä»¬
    0.09
    ä»Ĭ天
    0.09
    ä»Ĭ天æĪij们
    0.08
    today
    0.08
    Tonight
    0.08
    ä½łä»¬çļĦ
    0.08
    Activations Density 0.247%

    No Known Activations