© 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. 26388
    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
    使çĶ¨èµ·æĿ¥
    -0.08
    apa
    -0.08
    éĤ£åı¯æĺ¯
    -0.08
    écu
    -0.07
    è°ģçŁ¥
    -0.07
    çu
    -0.07
     smak
    -0.07
    ostas
    -0.07
    æĪijè¦ģè¯Ħ论
    -0.07
    éĤ£åı¯
    -0.07
    POSITIVE LOGITS
    _basis
    0.06
    NB
    0.06
    assi
    0.06
    orto
    0.06
    è´£
    0.06
    ç½®
    0.06
    æī¶
    0.06
    дем
    0.06
    lig
    0.06
    fk
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.