© 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. 20461
    Prev
    Next
    INDEX
    Explanations

    code length indicators

    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
    eken
    -0.07
    ometric
    -0.07
    chy
    -0.07
    ecker
    -0.07
    ÅĽÄĩ
    -0.07
    estat
    -0.07
    rän
    -0.07
    çļĦéĤ£ä¸ªäºº
    -0.06
    çļĦæŶåĢĻä¸Ģå®ļè¦ģ
    -0.06
    urÄĥ
    -0.06
    POSITIVE LOGITS
    +len
    0.07
    .Safe
    0.07
    ार
    0.07
     пÑĢон
    0.07
    walker
    0.06
    ensiones
    0.06
    ][]
    0.06
    IPP
    0.06
    ç§į
    0.06
    wash
    0.06
    Activations Density 0.035%

    No Known Activations