© 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. 14484
    Prev
    Next
    INDEX
    Explanations

    programmatic file extensions

    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
     lắm
    -0.07
    zl
    -0.07
    abia
    -0.07
    æĹłåīį
    -0.07
    lickr
    -0.07
    ê¸ī
    -0.06
    ÏĦÏģο
    -0.06
    kini
    -0.06
    ÙħÛĮÙĨ
    -0.06
    ropa
    -0.06
    POSITIVE LOGITS
    å®ģ
    0.08
    使ä¹ĭ
    0.07
    ënd
    0.07
    opoulos
    0.07
    illion
    0.07
    åħ¶ä¸ŃçļĦ
    0.07
    icamente
    0.07
    åİļå¾·
    0.07
    _Offset
    0.07
    iface
    0.06
    Activations Density 0.001%

    No Known Activations