© 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. 65379
    Prev
    Next
    INDEX
    Explanations

    convert, serialize, get keys/values

    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
    åĻ
    -0.07
    å´İ
    -0.07
    å¤įåIJĪåŀĭ
    -0.07
    (kind
    -0.06
    lesa
    -0.06
    pond
    -0.06
     nowhere
    -0.06
    elis
    -0.06
    addItem
    -0.06
    ç½®
    -0.06
    POSITIVE LOGITS
    .convert
    0.10
    Serialize
    0.09
    ToStr
    0.08
    Readable
    0.08
     converting
    0.08
    .serialize
    0.08
    Converted
    0.08
    ån
    0.08
     convert
    0.08
    åį³åı¯æŁ¥çľĭ
    0.08
    Activations Density 0.103%

    No Known Activations