© 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. 50189
    Prev
    Next
    INDEX
    Explanations

    type parameters, placeholders, or variables

    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
    remen
    -0.08
    çĬ¶æĢģä¸ĭ
    -0.08
    笳
    -0.07
    å±ħåīį
    -0.07
    ãģ¾ãģ¾ãģ§
    -0.07
    èĮ
    -0.07
    æijĬ
    -0.07
    æ¦Ħ
    -0.07
    intl
    -0.07
    Ĵ
    -0.07
    POSITIVE LOGITS
    彼岸
    0.08
    é£ŀè·ĥ
    0.07
    holm
    0.07
    稳
    0.07
     eventual
    0.07
    vert
    0.06
    @@
    0.06
    ced
    0.06
     logically
    0.06
    lein
    0.06
    Activations Density 0.006%

    No Known Activations