© 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. 22056
    Prev
    Next
    INDEX
    Explanations

    extreme conditions and measurements

    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
     dagegen
    -0.09
    ä¸įéĤ£ä¹Ī
    -0.09
     вдÑĢÑĥг
    -0.08
     hingegen
    -0.08
     nicely
    -0.08
    æݨ翻
    -0.07
    çĽ
    -0.07
     Spicer
    -0.07
     invece
    -0.07
     reasonably
    -0.07
    POSITIVE LOGITS
    æŀģ
    0.10
    æŀģèĩ´
    0.09
    åĪ°æŀģèĩ´
    0.09
    èĩ³æŀģ
    0.09
     extreme
    0.09
    åIJįåī¯åħ¶å®ŀçļĦ
    0.08
    è¿ijä¹İ
    0.08
    極
    0.08
    æŀģé«ĺçļĦ
    0.08
     extremely
    0.08
    Activations Density 0.336%

    No Known Activations