© 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. 33770
    Prev
    Next
    INDEX
    Explanations

    dialogue interactions

    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
    ths
    -0.08
    erv
    -0.07
    olt
    -0.07
    iling
    -0.07
    çĶ¸
    -0.07
    ward
    -0.07
    1
    -0.07
    大家åºŃ
    -0.07
    Ĺ
    -0.07
    หมาย
    -0.06
    POSITIVE LOGITS
    ues
    0.09
    reopen
    0.09
    unlock
    0.08
    ед
    0.08
    achine
    0.08
    truncate
    0.08
    aison
    0.08
    agne
    0.08
    conti
    0.08
    iseau
    0.08
    Activations Density 0.032%

    No Known Activations