© 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. 41009
    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
    æĽ´çĶŁ
    -0.08
    verity
    -0.07
    rena
    -0.07
    odos
    -0.07
    PROFILE
    -0.07
    åħ¶çľŁå®ŀæĢ§
    -0.07
     اÙĦصاد
    -0.07
    æī«é»ij
    -0.07
    çľŁå¯¦
    -0.07
     PROFILE
    -0.07
    POSITIVE LOGITS
    æ¯ı人
    0.08
    æŃ¤åľ°
    0.07
    æľĢå¤ļçļĦ
    0.06
    åĪĨéħįåĪ°
    0.06
    åĤ¨
    0.06
    æĬķãģĴ
    0.06
     Animated
    0.06
     Alloc
    0.06
     Equip
    0.06
     alloc
    0.06
    Activations Density 0.000%

    No Known Activations