© 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. 45494
    Prev
    Next
    INDEX
    Explanations

    given an IF

    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
    æ§ĭ
    -0.07
    ÑĨо
    -0.07
    åĪ°çĽ®åīį
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    "]]
    -0.06
    åĴ¸å®ģ
    -0.06
    ãģ¾ãģĦ
    -0.06
    s
    -0.06
    BJECT
    -0.06
    å¯¹åľ¨
    -0.06
    POSITIVE LOGITS
    رÙģتÙĩ
    0.08
    ajib
    0.08
    amber
    0.07
    ulina
    0.07
    ingham
    0.07
     ...)
    0.07
    hout
    0.07
    antica
    0.07
    uda
    0.07
    _CONV
    0.07
    Activations Density 0.003%

    No Known Activations