© 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. 33651
    Prev
    Next
    INDEX
    Explanations

    conditions after attaching

    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
    缺ä¸Ģ
    -0.08
    ħ
    -0.08
    imizer
    -0.07
    使å®ĥ
    -0.07
    åľ¨ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.07
    ä¹ĭä¸ĢçļĦ
    -0.07
    缨
    -0.07
    对该
    -0.07
    éĹ
    -0.06
    è¿Ľåİ»
    -0.06
    POSITIVE LOGITS
    åĩºçİ°åľ¨
    0.12
    åŃĺåľ¨äºİ
    0.11
    å¹¿æ³ĽåºĶçĶ¨äºİ
    0.10
     aboard
    0.10
    åĪĨå¸ĥåľ¨
    0.09
    åĩºçı¾åľ¨
    0.09
    è§ģäºİ
    0.09
     embedded
    0.09
     contained
    0.09
     accompanying
    0.09
    Activations Density 1.151%

    No Known Activations