© 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. 60577
    Prev
    Next
    INDEX
    Explanations

    break followed by specific words

    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
    urga
    -0.11
    verture
    -0.09
    kirchen
    -0.09
    -0.09
    inally
    -0.09
    marshall
    -0.09
    versión
    -0.09
    ibert
    -0.09
    chemy
    -0.09
    ненко
    -0.09
    POSITIVE LOGITS
    s
    0.08
    o
    0.08
    um
    0.08
    ness
    0.07
    ets
    0.07
    سر
    0.07
    andid
    0.07
    ake
    0.06
    åĥµå±Ģ
    0.06
    eworthy
    0.06
    Activations Density 0.036%

    No Known Activations