© 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. 21801
    Prev
    Next
    INDEX
    Explanations

    and followed by an important word

    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
    enga
    -0.07
    ossi
    -0.07
     Zar
    -0.07
    kir
    -0.07
    åħĭåħ°
    -0.07
    umper
    -0.06
    åĨįæİ¥åĨį
    -0.06
    avourite
    -0.06
    -Za
    -0.06
    æĹłå¸¸
    -0.06
    POSITIVE LOGITS
    æŃ£åĽł
    0.08
     damn
    0.08
    大åĮħ
    0.08
    czyn
    0.07
    æ¤Ĵ
    0.07
    带çļĦ
    0.07
    inox
    0.07
    žo
    0.06
    esine
    0.06
    sb
    0.06
    Activations Density 0.801%

    No Known Activations