© 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. 14806
    Prev
    Next
    INDEX
    Explanations

    well-defined, existence, meaningful

    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
    .nodeType
    -0.08
    »
    -0.08
    æĺ¥æĿ¥
    -0.08
    æĪĸèĢħåħ¶ä»ĸ
    -0.07
    éĻ£
    -0.07
    orris
    -0.07
    irmware
    -0.07
    θαν
    -0.07
    quil
    -0.07
    åĩºåĬ¨
    -0.07
    POSITIVE LOGITS
    æĶ¾å¿ĥ
    0.08
    ness
    0.08
    place
    0.08
    çĻĸ
    0.07
    ê³ł
    0.07
    -place
    0.07
    Ïģο
    0.07
    äºĨåľ¨
    0.06
    å±¹
    0.06
     place
    0.06
    Activations Density 0.002%

    No Known Activations