© 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. 31309
    Prev
    Next
    INDEX
    Explanations

    Carteret, Winter War, video player, arm, First, Today, Camp

    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
    åłµ
    -0.07
    ains
    -0.06
     b
    -0.06
    aca
    -0.06
    elts
    -0.06
     rif
    -0.06
    OMO
    -0.06
     doc
    -0.06
    ush
    -0.06
    oked
    -0.06
    POSITIVE LOGITS
    áĥķáĥĺ
    0.07
    नà¥ĩ
    0.07
    _opcode
    0.07
    pong
    0.07
     Loa
    0.07
    deaux
    0.07
    lie
    0.07
    æĽ´å¤ļèµĦ讯
    0.07
    pagesize
    0.07
    føl
    0.07
    Activations Density 0.316%

    No Known Activations