© 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. 23346
    Prev
    Next
    INDEX
    Explanations

    data structure types

    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
    )":
    -0.08
    ester
    -0.08
    ":
    -0.08
     nearby
    -0.08
    让å®ĥ们
    -0.07
    "":
    -0.07
    áÅĻ
    -0.07
    _abstract
    -0.07
    nist
    -0.07
    åįģäºĶæĹ¥åĨħ
    -0.07
    POSITIVE LOGITS
     representing
    0.07
    æĬķèµĦæĪĸ
    0.07
    ente
    0.06
     boh
    0.06
    çĥ¦
    0.06
    许诺
    0.06
     represents
    0.06
    iano
    0.06
    asin
    0.06
    çħ©
    0.06
    Activations Density 0.004%

    No Known Activations