© 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. 25695
    Prev
    Next
    INDEX
    Explanations

    move or relocate

    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
    å¼ĢéŨ
    -0.08
    家家
    -0.07
    %!
    -0.07
    Ñĥжи
    -0.07
    亲çİĭ
    -0.07
    éºŁ
    -0.07
    elli
    -0.07
    wic
    -0.07
     Emit
    -0.07
    anz
    -0.06
    POSITIVE LOGITS
    移åĪ°
    0.16
    移
    0.15
    移èĩ³
    0.15
    转移
    0.14
    转移åĪ°
    0.14
    ยà¹īาย
    0.14
    è¿ģ移
    0.13
    移åĬ¨åĪ°
    0.13
     transfer
    0.13
     onto
    0.13
    Activations Density 0.311%

    No Known Activations