© 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. 11753
    Prev
    Next
    INDEX
    Explanations

    EQU Fe

    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
    ĻĤ
    -0.08
    <dd
    -0.08
    dej
    -0.07
    rie
    -0.07
    以ä¸ĭåĩłçĤ¹
    -0.07
    轻信
    -0.07
    @brief
    -0.07
    essen
    -0.07
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    -0.07
    /cgi
    -0.07
    POSITIVE LOGITS
    0.07
    arth
    0.07
     Nied
    0.07
    ght
    0.07
    zÄĥ
    0.06
    <|box_end|>
    0.06
    å©ķ
    0.06
    浦
    0.06
    ä¹į
    0.06
    posit
    0.06
    Activations Density 0.004%

    No Known Activations