© 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. 47031
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    اء
    -0.08
    æĸ°éĥ½
    -0.08
     thereof
    -0.07
    oid
    -0.07
    иÑĤÑģÑı
    -0.07
    àªĤ
    -0.07
    é¦į
    -0.07
     Ellison
    -0.07
    eness
    -0.07
    _alive
    -0.07
    POSITIVE LOGITS
    åºĶå½ĵä¾Ŀçħ§
    0.07
    åºĶå½ĵåľ¨
    0.07
    èĩ³åħ³
    0.06
    æ¯Ķäºļ
    0.06
    çĥŃ忱
    0.06
     Tanjung
    0.06
    æł¹æľ¬æ²¡æľī
    0.06
    à¸Ĺัà¹īà¸ĩสิà¹īà¸Ļ
    0.06
    .hd
    0.06
    менÑĤаÑĢ
    0.06
    Activations Density 0.000%

    No Known Activations