© 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. 47281
    Prev
    Next
    INDEX
    Explanations

    beginning of phrases

    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
     "..
    -0.09
     anyways
    -0.08
     "\(
    -0.07
     appunto
    -0.07
     geler
    -0.07
    hoto
    -0.07
     bulunmaktadır
    -0.07
    éļıçĿĢæŶéĹ´çļĦæݨ移
    -0.07
    çļĦå°±
    -0.07
    thora
    -0.07
    POSITIVE LOGITS
    âĢij
    0.07
    ij
    0.07
     decisive
    0.07
     layered
    0.07
     downstream
    0.07
     –
    0.07
     specialised
    0.06
     emerging
    0.06
    èĩ
    0.06
    èµŀ
    0.06
    Activations Density 0.006%

    No Known Activations