© 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. 57381
    Prev
    Next
    INDEX
    Explanations

    links starting with http

    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
    unner
    -0.09
    irr
    -0.08
    ewe
    -0.08
    êt
    -0.08
    幡
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    ç«
    -0.07
    äge
    -0.07
    estia
    -0.07
    UNS
    -0.07
    POSITIVE LOGITS
     ur
    0.07
    客æľįçĥŃ线
    0.07
    idah
    0.07
    ëĿ¼ìĿ´
    0.07
    plice
    0.06
    ãĥ¼ãĤ¸ãĥ¼
    0.06
    ÑĢеменно
    0.06
    lasses
    0.06
     iż
    0.06
    deo
    0.06
    Activations Density 0.048%

    No Known Activations