© 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. 1396
    Prev
    Next
    INDEX
    Explanations

    define or accompanying

    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
    ikos
    -0.07
    rid
    -0.07
    uder
    -0.06
    enk
    -0.06
    å·§åIJĪ
    -0.06
     rok
    -0.06
    ÏĤ
    -0.06
    iento
    -0.06
    ogenesis
    -0.06
    clide
    -0.06
    POSITIVE LOGITS
    ocken
    0.08
    ustin
    0.08
    åıªè¦ģèĥ½
    0.07
    allinen
    0.07
    åĪĩå®ŀåģļåĪ°
    0.07
    å±Ĭ
    0.07
     Dalla
    0.07
    æľªåħį
    0.07
    ÑĦÑĥ
    0.07
    åįģåĪĨçļĦ
    0.07
    Activations Density 0.005%

    No Known Activations