© 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. 42422
    Prev
    Next
    INDEX
    Explanations

    numbers and specific characters

    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
     dụ
    -0.08
    åĪ«èĩ´
    -0.08
    ä¹İåħ¶
    -0.08
    маÑı
    -0.08
    ẹo
    -0.08
    anÃŃ
    -0.08
    elio
    -0.08
    ahaya
    -0.08
    æİĸ
    -0.08
    çĤľ
    -0.08
    POSITIVE LOGITS
    åľ°å¹³
    0.07
    衬
    0.07
    bl
    0.06
    填满
    0.06
    å¹³åĿ¦
    0.06
    aked
    0.06
    度è¿ĩ
    0.06
    osu
    0.06
     mut
    0.06
    éĻ¤åİ»
    0.06
    Activations Density 0.012%

    No Known Activations