© 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. 11285
    Prev
    Next
    INDEX
    Explanations

    memory cell

    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
    emor
    -0.07
    am
    -0.07
    undi
    -0.07
     sure
    -0.07
    amakan
    -0.07
    ame
    -0.06
    å¹²
    -0.06
    åĮĹå¸Ĥ
    -0.06
    éĽĦ
    -0.06
    ummy
    -0.06
    POSITIVE LOGITS
     individual
    0.19
     individually
    0.17
     Individual
    0.17
     individuel
    0.16
    åĢĭåĪ¥
    0.16
    individual
    0.16
     individuales
    0.16
     individuale
    0.15
    个ä½ĵ
    0.15
     individuais
    0.15
    Activations Density 0.783%

    No Known Activations