© 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. 29644
    Prev
    Next
    INDEX
    Explanations

    softness

    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
    juÄį
    -0.08
     nutshell
    -0.08
    onta
    -0.07
    ujur
    -0.07
    å¾Īæ¸ħæ¥ļ
    -0.07
    .Assertions
    -0.07
    é£İäºij
    -0.07
    èį£åħī
    -0.06
    亦ä¹IJä¹İ
    -0.06
    nicz
    -0.06
    POSITIVE LOGITS
    软çļĦ
    0.13
    æŁĶ
    0.12
     nhÃłng
    0.11
    soft
    0.11
    æŁĶ软
    0.11
    软
    0.11
    ness
    0.11
    æŁĶåĴĮ
    0.11
    æŁĶç¾İ
    0.10
     soft
    0.10
    Activations Density 0.050%

    No Known Activations