© 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. 26069
    Prev
    Next
    INDEX
    Explanations

    place names ending in ia, r, or 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
    èĩªæĭħ
    -0.08
    åĥıæĪij
    -0.08
    combe
    -0.07
    é¯ĸ
    -0.07
    agno
    -0.07
    輩
    -0.07
     magg
    -0.07
    æĬĬéĴ±
    -0.07
    urdy
    -0.07
    罡
    -0.07
    POSITIVE LOGITS
    æĪĺçķ¥æĢ§
    0.10
    æĪĺçķ¥
    0.09
     adjoining
    0.09
     holdings
    0.09
     coveted
    0.09
     lucrative
    0.09
     strategic
    0.09
    çļĦæĪĺçķ¥
    0.09
    以åıĬä¸İ
    0.08
     territories
    0.08
    Activations Density 0.388%

    No Known Activations