© 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. 51486
    Prev
    Next
    INDEX
    Explanations

    as the

    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
    1
    -0.08
    2
    -0.07
    0
    -0.07
     Hopkins
    -0.06
    _=
    -0.06
    ηÏĤ
    -0.06
    ÑĥÑī
    -0.06
    å¿
    -0.06
    ('{
    -0.06
    itable
    -0.06
    POSITIVE LOGITS
    .flat
    0.09
    该åĨħ容
    0.08
    isser
    0.08
    jong
    0.08
    SSI
    0.08
    cket
    0.07
    PIPE
    0.07
    çĶ¸
    0.07
    ;;;;
    0.07
    CUDA
    0.07
    Activations Density 0.069%

    No Known Activations