© 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. 45021
    Prev
    Next
    INDEX
    Explanations

    combine slapped nurse My win Cir

    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
    å°½æĺ¾
    -0.07
     inc
    -0.06
    åıªèĥ½è¯´
    -0.06
    ιÏĥη
    -0.06
    egment
    -0.06
    utsch
    -0.06
     pall
    -0.06
     voire
    -0.06
    ypress
    -0.06
    ä»ħéľĢ
    -0.06
    POSITIVE LOGITS
    ulls
    0.08
    ä¹ĿéľĦ
    0.08
    yman
    0.07
    gul
    0.07
    åĥıæĪij
    0.07
    ç»Ķ
    0.07
    ftar
    0.07
    rody
    0.07
    å¾·åĪ©
    0.07
    னà¯ģ
    0.07
    Activations Density 0.007%

    No Known Activations