© 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. 60709
    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
    ãĤģãģ§
    -0.06
    USES
    -0.06
    å¹²
    -0.06
    eso
    -0.06
    å¹²çļĦ
    -0.06
    auty
    -0.06
    çIJĨäºĭ
    -0.06
    datable
    -0.06
    çĦ¶åIJİåĨį
    -0.06
    à®®à¯įப
    -0.06
    POSITIVE LOGITS
    urve
    0.08
    çĥŃçĥĪç¥Ŀè´º
    0.08
    alah
    0.07
    วà¸ĩ
    0.07
    _relationship
    0.07
    _ING
    0.07
    çķ
    0.07
    åѦçĶŁå®¶éķ¿
    0.07
    è´¹åĴĮ
    0.07
    _strlen
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.