© 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. 10781
    Prev
    Next
    INDEX
    Explanations

    fungi, bacteria, or antibiotics

    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
    çĽIJåĴĮ
    -0.09
    emps
    -0.08
    поÑĢÑĤ
    -0.08
    åĪĿè§ģ
    -0.08
    ä¸İå®ŀè·µ
    -0.08
     Heidel
    -0.08
    оÑģÑĥ
    -0.08
    اÛĮØ´
    -0.07
    /settingsdialog
    -0.07
    yeti
    -0.07
    POSITIVE LOGITS
    èķ
    0.06
     cl
    0.06
    flies
    0.06
    itus
    0.06
    饥
    0.06
     Hier
    0.06
     J
    0.06
     proper
    0.06
    åħ¶ä»ĸåľ°åĮº
    0.06
    eres
    0.05
    Activations Density 1.071%

    No Known Activations