© 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. 58468
    Prev
    Next
    INDEX
    Explanations

    leaving or vacating

    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
     ras
    -0.07
    ç²¾èī¯
    -0.06
    è¢
    -0.06
     bows
    -0.06
    adder
    -0.06
    менов
    -0.06
    大åı£
    -0.06
    .reflect
    -0.06
    å¾ģ
    -0.06
    resse
    -0.06
    POSITIVE LOGITS
    çķĻå®Ī
    0.13
    æĹłäºº
    0.13
    çĦ¡äºº
    0.13
    çķĻè¨Ģ
    0.12
     overnight
    0.12
    è¿ĩå¤ľ
    0.11
    attended
    0.11
     оÑģÑĤавлÑıÑĤÑĮ
    0.10
    åĢ¼å®Ī
    0.10
    代为
    0.10
    Activations Density 0.168%

    No Known Activations