© 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. 51713
    Prev
    Next
    INDEX
    Explanations

    probability of picking letters

    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
     jaz
    -0.08
    [ID
    -0.08
    £¼
    -0.07
    potr
    -0.07
    çĢı
    -0.07
    otate
    -0.07
    èħ³è¸ı
    -0.07
     Potr
    -0.07
    autical
    -0.07
    दà¥įया
    -0.07
    POSITIVE LOGITS
    浩
    0.07
    LEAN
    0.06
     RIS
    0.06
    nock
    0.06
    ARO
    0.06
     subjects
    0.06
    aje
    0.06
    é»ĺ
    0.06
    æĥ³è®©
    0.06
    erus
    0.06
    Activations Density 0.036%

    No Known Activations