© 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. 29513
    Prev
    Next
    INDEX
    Explanations

    topics related to comparison or transition

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     either
    -0.07
     certainly
    -0.06
    è¦ģä¹Ī
    -0.06
    tracts
    -0.06
    éļĺ
    -0.06
    HING
    -0.06
    æīĢæĢĿ
    -0.06
    å½¢èī²
    -0.06
    orem
    -0.06
    æľīäºĭ
    -0.05
    POSITIVE LOGITS
     vs
    0.12
     versus
    0.11
    çļĦåħ¶ä»ĸ
    0.10
    çŃīåħ¶ä»ĸ
    0.10
    "":
    0.09
     #:
    0.09
     ÙĪÙĥÙĬÙģ
    0.08
    _vs
    0.08
    }:
    0.08
    ]:
    0.08
    Activations Density 0.014%

    No Known Activations