© 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. 51019
    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
    åı¯æĢľçļĦ
    -0.08
    <|box_end|>
    -0.08
    Ñİза
    -0.08
    anst
    -0.07
    à¸Ħา
    -0.07
     Doll
    -0.07
     severed
    -0.07
    acula
    -0.07
    åħ·å¤ĩäºĨ
    -0.07
    å¨ĥå¨ĥ
    -0.06
    POSITIVE LOGITS
    irie
    0.07
    åıĺ
    0.07
    rust
    0.07
    tyw
    0.07
    raag
    0.07
    nameof
    0.07
    isd
    0.06
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.06
    åĴĮäºĮ
    0.06
    dy
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.