© 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. 4263
    Prev
    Next
    INDEX
    Explanations

    copyright symbol followed by year

    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
    E
    -0.07
    ystal
    -0.07
    rastructure
    -0.07
    /ext
    -0.07
    T
    -0.07
    O
    -0.07
    gether
    -0.06
    ÙĨ
    -0.06
    R
    -0.06
    æ±Łè¾¹
    -0.06
    POSITIVE LOGITS
    jenigen
    0.12
    orem
    0.11
    esium
    0.10
    sWith
    0.09
     Metropolitana
    0.09
    scher
    0.09
    icitÃł
    0.08
    incinn
    0.08
    rippling
    0.08
    psilon
    0.08
    Activations Density 1.599%

    No Known Activations