© 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. 11518
    Prev
    Next
    INDEX
    Explanations

    second position or occurrence

    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
    andes
    -0.10
    éĤ¸
    -0.10
    getto
    -0.09
    tober
    -0.09
    ünt
    -0.09
    odata
    -0.09
    esti
    -0.09
    ../
    -0.09
    ahas
    -0.09
    çĻ¾å·Ŀ
    -0.09
    POSITIVE LOGITS
    aries
    0.12
    -feira
    0.11
    arily
    0.10
    -tier
    0.09
    ly
    0.09
     kalinya
    0.08
    halb
    0.08
    (er
    0.08
    -generation
    0.08
    -hand
    0.08
    Activations Density 0.076%

    No Known Activations