© 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. 31122
    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
    æ·¹
    -0.06
    idth
    -0.06
    ä½ľåģĩ
    -0.06
    cion
    -0.06
    unik
    -0.06
    SSI
    -0.06
    人éĥ½
    -0.06
    润èĤº
    -0.06
     Port
    -0.06
     unpack
    -0.06
    POSITIVE LOGITS
     Finch
    0.08
    衣帽
    0.08
     ìĤŃ
    0.08
    ceptors
    0.07
    arget
    0.07
    ergeb
    0.07
    .press
    0.07
    arga
    0.07
    åħĭåĪ©
    0.07
    ceptor
    0.07
    Activations Density 0.000%

    No Known Activations