© 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. 3474
    Prev
    Next
    INDEX
    Explanations

    locations and segments

    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
    对被
    -0.07
    astien
    -0.06
    ält
    -0.06
    åľı
    -0.06
    lag
    -0.06
    amental
    -0.06
     world
    -0.06
    Magn
    -0.06
    iren
    -0.06
     kval
    -0.06
    POSITIVE LOGITS
    нÑĤо
    0.09
    åıĺæĽ´ä¿¡æģ¯
    0.08
    äºĮéĥİ
    0.07
    ToDelete
    0.07
    åĽłæ¶īå«Į
    0.07
    ONY
    0.07
    平衡
    0.07
     Romana
    0.07
    иÑĤаÑĢ
    0.07
    çĶĺå¿ĥ
    0.07
    Activations Density 0.002%

    No Known Activations