© 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. 27750
    Prev
    Next
    INDEX
    Explanations

    corrupted Cyrillic characters

    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
    mente
    -0.10
    bourg
    -0.09
    rhein
    -0.09
    amente
    -0.09
    lö
    -0.09
    stown
    -0.08
    ippines
    -0.08
    voud
    -0.08
    ê»ĺ
    -0.08
    lement
    -0.08
    POSITIVE LOGITS
    аем
    0.08
    çļĦ
    0.08
     behalf
    0.08
    liness
    0.07
    sWith
    0.07
    и
    0.07
    ãģ®ãģ§ãģĤãĤĮãģ°
    0.07
    eut
    0.07
    esi
    0.07
    0.07
    Activations Density 0.010%

    No Known Activations