© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42282
    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
    ges
    -0.06
     Cock
    -0.06
    lock
    -0.06
    _embed
    -0.06
    æ½ĩ
    -0.06
     gal
    -0.06
    çĭ¬è§Ĵ
    -0.06
     nob
    -0.05
     heter
    -0.05
    æ¿Ģæ´»
    -0.05
    POSITIVE LOGITS
    _SID
    0.09
    ahl
    0.09
    è¾ĵ
    0.08
    ัà¹īà¸ĩ
    0.08
    fdc
    0.08
    dou
    0.08
    yac
    0.08
    구ìĹIJ
    0.08
    ousse
    0.08
    -parameter
    0.08
    Activations Density 0.000%

    No Known Activations