© 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. 1017
    Prev
    Next
    INDEX
    Explanations

    question answering involving numbers

    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
    èĢ½
    -0.07
    usine
    -0.07
    ivered
    -0.07
    çĤ¯
    -0.07
    æ»ĭ
    -0.07
    æ¶ķ
    -0.07
    æ§Ľ
    -0.06
    erville
    -0.06
    enu
    -0.06
    Asked
    -0.06
    POSITIVE LOGITS
    upati
    0.08
    รà¸Ńà¸ĩ
    0.07
     Bast
    0.07
    @register
    0.07
    _locals
    0.07
    åĴĮéĹ®é¢ĺ
    0.06
    istar
    0.06
     keinem
    0.06
    @qq
    0.06
    ׼ף
    0.06
    Activations Density 0.004%

    No Known Activations