© 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. 46981
    Prev
    Next
    INDEX
    Explanations

    estimating converting sales introducing

    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
    åĬŁ
    -0.07
     due
    -0.07
    ekan
    -0.06
     debido
    -0.06
    çĶ±äºİ
    -0.06
     Due
    -0.06
    åİĨåı²çļĦ
    -0.06
     obviamente
    -0.06
    due
    -0.06
    Obviously
    -0.06
    POSITIVE LOGITS
    huri
    0.08
    ÄĻg
    0.08
    eningen
    0.08
    æĺĬ天
    0.08
    éģĵ人
    0.07
     indeed
    0.07
    енÑĮе
    0.07
    anÃŃ
    0.07
    yorum
    0.07
    çļĦç¡®
    0.07
    Activations Density 0.086%

    No Known Activations