© 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. 20204
    Prev
    Next
    INDEX
    Explanations

    math equations (let b)

    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
    ccion
    -0.08
    asten
    -0.08
    uhl
    -0.07
    zyd
    -0.07
     εγκ
    -0.07
    -extra
    -0.07
    å·²çĦ¶
    -0.07
     ÑĢаÑģка
    -0.07
    holz
    -0.07
    ÙĪات
    -0.07
    POSITIVE LOGITS
    mite
    0.08
    ä¸ĢèģĬ
    0.08
    éĺĻ
    0.07
    orni
    0.07
    iran
    0.06
    ban
    0.06
    atted
    0.06
    ä¹ĭæ¯į
    0.06
    ä¸ij
    0.06
    fter
    0.06
    Activations Density 0.006%

    No Known Activations