© 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. 12116
    Prev
    Next
    INDEX
    Explanations

    million records

    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
    ihak
    -0.09
    MASK
    -0.08
    Canceled
    -0.08
     posteri
    -0.08
    çĻ¾å®¶
    -0.08
    hyl
    -0.08
    çķ¦
    -0.08
    CharCode
    -0.08
    endor
    -0.07
    UCA
    -0.07
    POSITIVE LOGITS
    à¹ģà¸ģà¹Ī
    0.06
    èŁĭ
    0.06
    åIJįä¹ī
    0.06
    reck
    0.06
    ahrt
    0.06
    ä¸ĢæĹ¥
    0.06
    à°¨à±ģ
    0.06
     range
    0.06
    åıĬ以ä¸ĬçļĦ
    0.06
    à¸ŀิ
    0.06
    Activations Density 0.002%

    No Known Activations