© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42521
    Prev
    Next
    INDEX
    Explanations

    items related to design and media

    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
    èijĨ
    -0.09
    mtree
    -0.09
    IMI
    -0.08
    imi
    -0.07
    èĩ´çļĦ
    -0.07
    UTT
    -0.07
    cpt
    -0.07
    dbg
    -0.07
    edur
    -0.07
    onan
    -0.07
    POSITIVE LOGITS
    å¼±èĢħ
    0.06
    ³
    0.06
    ubl
    0.06
    ernos
    0.06
    lab
    0.06
    enti
    0.06
    umen
    0.06
    stag
    0.06
    infer
    0.06
    øv
    0.06
    Activations Density 0.007%

    No Known Activations