© 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. 56061
    Prev
    Next
    INDEX
    Explanations

    rear of something

    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
    ÑĤÑģÑı
    -0.08
    zó
    -0.08
    å¤ĸ人
    -0.07
    gados
    -0.07
    æĽĻ
    -0.07
    ekar
    -0.07
    AtPath
    -0.07
    oureux
    -0.07
    æķĸ
    -0.07
    ollar
    -0.07
    POSITIVE LOGITS
    (back
    0.12
    /back
    0.11
     belakang
    0.11
     behind
    0.09
     lÆ°ng
    0.09
    ward
    0.08
    åĴĮåīį
    0.08
    åĢĴéĢĢ
    0.08
    =back
    0.08
    ยาว
    0.08
    Activations Density 0.099%

    No Known Activations