© 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. 61562
    Prev
    Next
    INDEX
    Explanations

    has/tem/possesses

    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
    lacement
    -0.09
    zens
    -0.07
    ми
    -0.07
    oload
    -0.07
    artige
    -0.07
    뾨
    -0.07
    ãĤºãģ®
    -0.07
    åıijå±ķçļĦéľĢè¦ģ
    -0.07
    ÙĨاÙħÙĩ
    -0.07
    alts
    -0.07
    POSITIVE LOGITS
    te
    0.10
    र
    0.09
    ered
    0.09
     thá»ĥ
    0.08
    র
    0.08
    o
    0.08
    er
    0.08
    пл
    0.08
    ron
    0.08
    Ø©
    0.08
    Activations Density 0.003%

    No Known Activations