© 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. 15094
    Prev
    Next
    INDEX
    Explanations

    weak + modifiers/suffixes

    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
    evat
    -0.10
     ulang
    -0.10
    enteri
    -0.09
    NewLabel
    -0.09
    OMIC
    -0.09
    agnost
    -0.09
    à¹ģà¸Ķà¸Ļ
    -0.08
    elek
    -0.08
    uera
    -0.08
    غت
    -0.08
    POSITIVE LOGITS
    ly
    0.14
    ened
    0.12
    ening
    0.12
    à¹Ĩ
    0.11
    ness
    0.10
    å¼±çļĦ
    0.10
    ÑģÑı
    0.10
    ëĤĺë§Ī
    0.09
    stens
    0.09
    lessly
    0.09
    Activations Density 0.012%

    No Known Activations