© 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. 63105
    Prev
    Next
    INDEX
    Explanations

    alternating

    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
    untu
    -0.09
    dana
    -0.08
    niec
    -0.08
    ainty
    -0.07
    eki
    -0.07
    endig
    -0.07
    öss
    -0.07
    eor
    -0.07
    erval
    -0.07
    ergestellt
    -0.07
    POSITIVE LOGITS
    ¯
    0.08
     nhau
    0.08
    ed
    0.08
    çĿĢçļĦ
    0.07
    ict
    0.07
    alous
    0.07
    éģķãģ£ãģŁ
    0.07
    ickness
    0.07
    ÑģÑı
    0.07
     xứng
    0.07
    Activations Density 0.016%

    No Known Activations