© 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. 56966
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     quit
    -0.08
    åIJįå±±
    -0.07
    izo
    -0.07
    uler
    -0.07
    ess
    -0.07
    å·¡è§Ĩåijĺ
    -0.07
    UnderTest
    -0.06
    çī©çļĦ
    -0.06
    quit
    -0.06
    ledo
    -0.06
    POSITIVE LOGITS
    è¿Ļä¸ªåľ°æĸ¹
    0.08
    çŃīåľ°çļĦ
    0.08
    letal
    0.08
    ä¹ĭæĪĺ
    0.08
    croft
    0.08
    ensis
    0.08
    çŃīå¤Ħ
    0.07
    çŃīä¸Ģç³»åĪĹ
    0.07
    åīįå¤ķ
    0.07
    çķĶ
    0.07
    Activations Density 0.090%

    No Known Activations