© 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. 19649
    Prev
    Next
    INDEX
    Explanations

    magnetic flux density **B**, contribution, terms, magnitude

    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
    igen
    -0.07
    æĸ°éĥ½
    -0.07
    sted
    -0.07
    åı¥åı¥
    -0.07
    pal
    -0.07
    éĩĩè´Ń人
    -0.06
     trials
    -0.06
    éĺ»æĸŃ
    -0.06
     пода
    -0.06
     Gro
    -0.06
    POSITIVE LOGITS
    velocity
    0.08
    çŁ¢éĩı
    0.08
     {*
    0.08
    schild
    0.08
    quantity
    0.08
    observable
    0.07
    aum
    0.07
     dõi
    0.07
    omentum
    0.07
     components
    0.07
    Activations Density 0.004%

    No Known Activations