© 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. 46699
    Prev
    Next
    INDEX
    Explanations

    address after ing

    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
    overrides
    -0.08
    literal
    -0.07
    etails
    -0.07
    ebab
    -0.07
     supers
    -0.07
    overs
    -0.07
    arde
    -0.07
    ushman
    -0.06
    uess
    -0.06
    idak
    -0.06
    POSITIVE LOGITS
    ابع
    0.07
    æ±Ľ
    0.07
    æ°Ķ象åı°
    0.07
    è¦ģæ±Ĥåľ¨
    0.07
    apis
    0.06
    æľ¯
    0.06
    æ¶ī
    0.06
     por
    0.06
    ãĥĬãĤ¹
    0.06
    icolore
    0.06
    Activations Density 0.008%

    No Known Activations