© 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. 27718
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    andal
    -0.08
    esda
    -0.08
    emaine
    -0.08
    "group
    -0.07
    ìľ
    -0.07
    æĪĸå°ij
    -0.07
     <![
    -0.07
    lø
    -0.07
    schild
    -0.07
    éĢļäºĨ
    -0.07
    POSITIVE LOGITS
    éļĻ
    0.07
    °
    0.07
    ocus
    0.07
    dg
    0.06
    ator
    0.06
    åłª
    0.06
    å¦į
    0.06
    osan
    0.06
    ators
    0.06
    kan
    0.06
    Activations Density 0.000%

    No Known Activations