© 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. 2793
    Prev
    Next
    INDEX
    Explanations

    versus, compared, trial, study

    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
    éŀŃ
    -0.08
    izen
    -0.07
    为äºĨæĽ´å¥½åľ°
    -0.06
    unami
    -0.06
    SIG
    -0.06
    hopefully
    -0.06
    å°½åı¯èĥ½çļĦ
    -0.06
    ignor
    -0.06
    oit
    -0.06
    丧失
    -0.06
    POSITIVE LOGITS
     randomized
    0.11
     trials
    0.09
     outcomes
    0.09
     trial
    0.09
     Trials
    0.09
     targ
    0.09
    è¯ķéªĮ
    0.08
     Trial
    0.08
    çļĦæķĪæŀľ
    0.08
     Compared
    0.08
    Activations Density 1.049%

    No Known Activations