© 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. 21950
    Prev
    Next
    INDEX
    Explanations

    citations and Brazilian states

    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
    icha
    -0.09
    è¿ľè¿ij
    -0.07
    å¤ĸçķĮ
    -0.07
    ersten
    -0.07
    å¤ļåĸĿ
    -0.07
    erven
    -0.07
    å¤ĸçķĮçļĦ
    -0.07
    pir
    -0.07
    kening
    -0.07
    (_:
    -0.07
    POSITIVE LOGITS
    åľ¨åħ¶
    0.10
    åħ¶äº§åĵģ
    0.09
    ç§ĭæľĪ
    0.07
    è·Łè´´
    0.07
    çĶ±äºİåħ¶
    0.07
    è¿ĺæıIJä¾ĽäºĨ
    0.07
    ä»İåħ¶
    0.07
    OG
    0.07
    åħ¶æŀĹ
    0.06
    çĶ±åħ¶
    0.06
    Activations Density 0.318%

    No Known Activations