© 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. 3163
    Prev
    Next
    INDEX
    Explanations

    == comparison

    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
    erio
    -0.11
    à§įà¦Ł
    -0.11
    à§įড
    -0.10
    eria
    -0.10
    ìį¨
    -0.10
    deaux
    -0.10
    paket
    -0.10
    Ö¼
    -0.10
    inha
    -0.10
    jÅ¡ÃŃ
    -0.10
    POSITIVE LOGITS
     nhau
    0.08
    åħ¶
    0.08
    åħ¶ä»ĸ
    0.07
    /=
    0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.07
    “
    0.06
    O
    0.06
    oureux
    0.06
    "
    0.06
    åĴĮ
    0.06
    Activations Density 0.015%

    No Known Activations