© 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. 57648
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by conjunctions or sequences

    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
    earned
    -0.07
    eczy
    -0.07
    иÑı
    -0.07
    çĶ¨æĪ·ä¸Ĭä¼ł
    -0.07
     prop
    -0.06
    æĢĢåŃķæľŁéĹ´
    -0.06
    port
    -0.06
    atakan
    -0.06
    å²ij
    -0.06
    EMI
    -0.06
    POSITIVE LOGITS
    çĦ¶åIJİ
    0.18
     then
    0.16
    çĦ¶åIJİåľ¨
    0.16
     سپس
    0.15
    çĦ¶å¾Į
    0.15
     заÑĤем
    0.15
     kemudian
    0.14
    çĦ¶åIJİéĢļè¿ĩ
    0.14
    çĦ¶åIJİçĶ¨
    0.14
     subsequently
    0.14
    Activations Density 0.528%

    No Known Activations