© 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. 8254
    Prev
    Next
    INDEX
    Explanations

    table, VERSION, Hungary, median, cost

    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
    åİŁä½ĵ
    -0.09
    çĨŁèĥ½
    -0.08
    ÙĬÙĦÙĩ
    -0.07
    AMPL
    -0.07
    ight
    -0.07
    ä½łåij¢
    -0.07
    Dire
    -0.07
    åĿ
    -0.07
    idet
    -0.07
     USAGE
    -0.07
    POSITIVE LOGITS
    firm
    0.07
     [...]
    0.07
    excerpt
    0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.06
    ...
    0.06
     [âĢ¦]
    0.06
    ç½ļ
    0.06
    cerpt
    0.06
    æĭĶ
    0.06
    ...</
    0.06
    Activations Density 0.063%

    No Known Activations