© 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. 31988
    Prev
    Next
    INDEX
    Explanations

    configuration information

    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
    обо
    -0.08
    è¿ĻæĬĬ
    -0.08
    isca
    -0.08
    ÙģÙĪ
    -0.08
    åĨħ容为
    -0.08
    ufen
    -0.07
    åīijæ°Ķ
    -0.07
    çIJ²
    -0.07
    åħ¬çĽĬäºĭä¸ļ
    -0.07
    oph
    -0.07
    POSITIVE LOGITS
    arts
    0.08
    éĴ¦
    0.07
    adx
    0.06
    atro
    0.06
    ¾
    0.06
     coefficients
    0.06
    åĩłçĤ¹
    0.06
    base
    0.06
    éĢ
    0.06
     highest
    0.06
    Activations Density 0.001%

    No Known Activations