© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46516
    Prev
    Next
    INDEX
    Explanations

    honey and bees

    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
    ally
    -0.08
    è¾ĵ尿管
    -0.07
    ures
    -0.07
    elsey
    -0.07
    imately
    -0.07
    alan
    -0.07
    åħīçĽĺ
    -0.07
    walt
    -0.07
    alty
    -0.07
    ³
    -0.06
    POSITIVE LOGITS
    èľĤèľľ
    0.10
     меда
    0.09
     bees
    0.09
    èľľ
    0.09
     madu
    0.09
    Apis
    0.08
     ê¿Ģ
    0.08
    èľľèľĤ
    0.08
     bee
    0.08
    bee
    0.08
    Activations Density 0.035%

    No Known Activations