© 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. 30331
    Prev
    Next
    INDEX
    Explanations

    factorization

    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
     tick
    -0.07
    venz
    -0.07
    èĩªçIJĨ
    -0.06
     зага
    -0.06
    模æĭŁè¯ķé¢ĺ
    -0.06
    zeÅĦ
    -0.06
    /tty
    -0.06
    å´İå²ĸ
    -0.06
    avia
    -0.06
    游走
    -0.06
    POSITIVE LOGITS
     Kalt
    0.08
    åħĭç½Ĺ
    0.08
    .Reader
    0.08
    ãĥ¼ãĥł
    0.08
    éĢłæĪIJ
    0.08
     ÑĨеликом
    0.08
     Vect
    0.08
    کت
    0.08
     vectors
    0.07
    olley
    0.07
    Activations Density 0.004%

    No Known Activations