© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10610
    Prev
    Next
    INDEX
    Explanations

    . following sentence start

    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
    vind
    -0.07
    AtPath
    -0.07
    cape
    -0.07
    iores
    -0.07
    imits
    -0.07
    (where
    -0.07
    istan
    -0.07
    ught
    -0.07
    ulto
    -0.07
    vier
    -0.07
    POSITIVE LOGITS
     based
    0.07
    èĩĬ
    0.07
    uki
    0.07
    å¾Īæĺİæĺ¾
    0.07
    ssen
    0.06
    æĴ©
    0.06
    æĺ¾çĦ¶
    0.06
    arken
    0.06
    åħĪçľĭ
    0.06
    ï¿£
    0.06
    Activations Density 0.101%

    No Known Activations