© 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. 16441
    Prev
    Next
    INDEX
    Explanations

    intermediate / intermediary

    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
    ess
    -0.07
    èĢĹ
    -0.07
    å·®
    -0.07
    -sign
    -0.06
    ass
    -0.06
    esson
    -0.06
    è¡¥
    -0.06
    第ä¸ĥæĿ¡
    -0.06
    esse
    -0.06
    åħį
    -0.06
    POSITIVE LOGITS
     intermediate
    0.10
     intermediary
    0.10
    Intermediate
    0.09
     intermedi
    0.09
     Intermediate
    0.09
     пÑĢомежÑĥ
    0.09
    æĮĿ
    0.08
     ì¤ijê°Ħ
    0.08
    æīĢåľ¨åįķä½į
    0.08
     >(
    0.08
    Activations Density 0.160%

    No Known Activations