© 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. 14568
    Prev
    Next
    INDEX
    Explanations

    region definitions

    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
    ä¹ĭè¾Ī
    -0.08
    åĽŀäºĭ
    -0.08
    yers
    -0.08
    à¸Ľà¸£à¸°à¸Īำ
    -0.08
    ango
    -0.08
    åħ¶ä¸º
    -0.07
    vester
    -0.07
    ä¹ĭå¤Ħåľ¨äºİ
    -0.07
    ition
    -0.07
    erton
    -0.07
    POSITIVE LOGITS
    aal
    0.10
    ally
    0.10
    ális
    0.10
    nement
    0.10
    naire
    0.09
    -wide
    0.09
    ROUP
    0.09
    फल
    0.09
    ettes
    0.09
    ãĥ£ãĥ³
    0.08
    Activations Density 0.092%

    No Known Activations