© 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. 25909
    Prev
    Next
    INDEX
    Explanations

    Belleville

    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
    è¨ĺ
    -0.06
    çīĩçīĩ
    -0.06
    idium
    -0.06
    EQ
    -0.06
    jist
    -0.06
    zio
    -0.06
    gre
    -0.06
    gf
    -0.06
    à¸Ķà¸Ńà¸Ļ
    -0.06
    onium
    -0.06
    POSITIVE LOGITS
     наконеÑĨ
    0.08
    ÑĢÑĥз
    0.08
    åħ¶ä¸ī
    0.08
    å°Ķ夫
    0.08
    omes
    0.07
    ouden
    0.07
    ourney
    0.07
    colar
    0.07
     trá»ĭ
    0.07
    aina
    0.07
    Activations Density 0.162%

    No Known Activations