© 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. 64206
    Prev
    Next
    INDEX
    Explanations

    reading file

    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
    æķħéĩĮ
    -0.07
    ffet
    -0.07
    zicht
    -0.07
     neither
    -0.07
    träger
    -0.06
    vie
    -0.06
    ibox
    -0.06
    -hover
    -0.06
    åIJİè£Ķ
    -0.06
    esel
    -0.06
    POSITIVE LOGITS
    åĴĮå¤ĦçIJĨ
    0.11
    /store
    0.10
    åĴĮçIJĨ解
    0.10
    åĴĮåĪĨæŀIJ
    0.09
    ream
    0.09
    oler
    0.08
    otten
    0.08
    into
    0.08
    AndUpdate
    0.08
    æķ°æį®è¿Ľè¡Į
    0.08
    Activations Density 0.060%

    No Known Activations