© 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. 26376
    Prev
    Next
    INDEX
    Explanations

    Âł followed by E N Y ch Yu A rab

    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
    aul
    -0.08
    angeb
    -0.08
    ilib
    -0.07
    алÑĮÑı
    -0.07
    ings
    -0.06
    atak
    -0.06
    igr
    -0.06
    éĩijé¾Ļ
    -0.06
    çľĭä¸Ģçľĭ
    -0.06
    -token
    -0.06
    POSITIVE LOGITS
    phans
    0.08
    vrier
    0.08
    ä¹ħä¹ĭ
    0.08
    ÑīеÑĤ
    0.08
    forth
    0.08
    geler
    0.07
     {}.
    0.07
    âĢ¦âĢ¦ãĢĤ
    0.07
    .newaxis
    0.07
    è¯¥ä½ľèĢħ
    0.07
    Activations Density 0.086%

    No Known Activations