© 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. 1196
    Prev
    Next
    INDEX
    Explanations

    alternatives or modifications

    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
    loch
    -0.08
    ingue
    -0.08
    Playable
    -0.08
    retch
    -0.08
    Began
    -0.07
    ä»»ä½ķ人
    -0.07
    enser
    -0.07
    illow
    -0.07
    _any
    -0.07
    åĬĽäºī
    -0.07
    POSITIVE LOGITS
     addirittura
    0.11
    å¹²èĦĨ
    0.11
     sogar
    0.11
    æł¹æľ¬å°±æĺ¯
    0.10
     outright
    0.10
    æł¹æľ¬å°±
    0.10
    æł¹æľ¬ä¸į
    0.10
     вовÑģе
    0.10
    åıįä¹ĭ
    0.09
    acles
    0.09
    Activations Density 0.141%

    No Known Activations