© 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. 27443
    Prev
    Next
    INDEX
    Explanations

    alternative options or equivalence

    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
    çĬĢ
    -0.08
    antik
    -0.08
    ä¸Ģæī¶
    -0.08
    å¸Ĥåºľ
    -0.08
    eor
    -0.07
    å®ŀå¤Ħ
    -0.07
    ä½ĨæĦ¿
    -0.07
    allon
    -0.07
    个åĽŀçŃĶ
    -0.07
    koch
    -0.07
    POSITIVE LOGITS
    using
    0.07
    æł¹æį®éľĢè¦ģ
    0.07
     alternatively
    0.07
    çĶ¨ä¸Ģ个
    0.07
    ally
    0.07
     alternativ
    0.07
     using
    0.06
    incon
    0.06
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.06
    ign
    0.06
    Activations Density 0.017%

    No Known Activations