© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2304
    Prev
    Next
    INDEX
    Explanations

    transferring or converting

    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
    çķĮ
    -0.07
    uren
    -0.06
    åĪ¹
    -0.06
    isnan
    -0.06
    åIJĪä¸Ģ
    -0.06
    çĻ¾äºº
    -0.06
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    СÐļ
    -0.06
    åĩĢ
    -0.06
    abh
    -0.06
    POSITIVE LOGITS
    transfer
    0.10
     transfer
    0.10
     Transfer
    0.10
    转æį¢
    0.10
    è°ĥæķ´
    0.09
    Transfer
    0.09
     transferring
    0.09
    .transfer
    0.09
    åĴĮè°ĥæķ´
    0.09
    转移
    0.08
    Activations Density 0.015%

    No Known Activations