© 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. 57093
    Prev
    Next
    INDEX
    Explanations

    Page followed by colon

    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
    ello
    -0.07
    esel
    -0.07
     inver
    -0.07
    alp
    -0.07
    ida
    -0.07
    emar
    -0.06
    iac
    -0.06
    _PARSER
    -0.06
    uman
    -0.06
    Äħż
    -0.06
    POSITIVE LOGITS
    ilhar
    0.08
    ìĬ¤íħĮ
    0.07
    hue
    0.07
    ãĥ©ãĥł
    0.07
     оÑĤÑĢ
    0.07
    Ïįν
    0.07
    zni
    0.07
    WithContext
    0.07
    cken
    0.07
    usul
    0.07
    Activations Density 0.066%

    No Known Activations