© 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. 34070
    Prev
    Next
    INDEX
    Explanations

    `2,%`

    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
    бе
    -0.08
    ughs
    -0.07
    abee
    -0.07
    urat
    -0.07
    abin
    -0.07
    æľĢä¼ĺç§ĢçļĦ
    -0.07
    æľĢå·®
    -0.06
    èºį
    -0.06
    rawer
    -0.06
    jay
    -0.06
    POSITIVE LOGITS
    seq
    0.08
    wives
    0.08
     Somma
    0.07
    .seq
    0.07
     seq
    0.07
    unan
    0.07
    çĥ½çģ«
    0.07
     onFocus
    0.07
    adam
    0.07
    Seq
    0.07
    Activations Density 0.046%

    No Known Activations