© 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. 34368
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    æĪ
    -0.08
    hist
    -0.07
    ÙĪاØŃ
    -0.07
    çŃ
    -0.07
    EMAIL
    -0.06
    argv
    -0.06
    ]=="
    -0.06
    è·»
    -0.06
    astic
    -0.06
    ="{{
    -0.06
    POSITIVE LOGITS
    acies
    0.07
    azia
    0.07
    azio
    0.07
    æĢ»è®¡
    0.07
    óp
    0.07
    以æŃ¤ä¸º
    0.07
    ÙĪتر
    0.07
    inkin
    0.07
    TOTAL
    0.07
    缸åĬł
    0.06
    Activations Density 0.062%

    No Known Activations