© 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. 63556
    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
    ousel
    -0.11
    lename
    -0.10
    amodel
    -0.09
    ocab
    -0.09
    ndef
    -0.09
    Ùĥات
    -0.09
    arate
    -0.09
    stad
    -0.09
    ÅĤow
    -0.09
    umpl
    -0.09
    POSITIVE LOGITS
    0.07
     anti
    0.07
     rand
    0.06
     complex
    0.06
     I
    0.06
     ant
    0.06
     B
    0.06
    +
    0.06
    ational
    0.06
     j
    0.06
    Activations Density 0.000%

    No Known Activations