© 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. 65250
    Prev
    Next
    INDEX
    Explanations

    sunshine, freezing, modern

    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
    çľģäºĭ
    -0.07
    Uri
    -0.07
    _fd
    -0.07
    rong
    -0.07
    _URI
    -0.07
     Exclusive
    -0.07
     ÑģобÑĸ
    -0.07
    aveur
    -0.07
    agus
    -0.06
    èµĦ产交æĺĵ
    -0.06
    POSITIVE LOGITS
     despite
    0.26
    尽管
    0.26
    èĻ½çĦ¶æĺ¯
    0.23
     Despite
    0.23
    èĻ½çĦ¶
    0.22
    Despite
    0.21
    èĻ½
    0.21
    èĻ½çĦ¶æĪij们
    0.21
     spite
    0.20
     неÑģмоÑĤÑĢÑı
    0.20
    Activations Density 0.249%

    No Known Activations