© 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. 45699
    Prev
    Next
    INDEX
    Explanations

    names with suffixes like Jr, III, Strauss, Lorenzo

    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
    uha
    -0.10
    loch
    -0.08
    ykk
    -0.08
    ynt
    -0.08
    ÃŃp
    -0.08
    yš
    -0.08
    :event
    -0.08
    ault
    -0.07
    rakt
    -0.07
    %C
    -0.07
    POSITIVE LOGITS
    µ
    0.07
    ANDLE
    0.07
    æ´ĭ
    0.06
    å¿ĥçĶ°
    0.06
    åĽ½
    0.06
     Jr
    0.06
    аÑĩ
    0.06
     extension
    0.06
    elijk
    0.06
    piler
    0.06
    Activations Density 0.312%

    No Known Activations