© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34010
    Prev
    Next
    INDEX
    Explanations

    proton or ton related prefixes/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
    NESS
    -0.10
    stral
    -0.09
    lector
    -0.09
    -vous
    -0.08
    iance
    -0.08
    è¿ijå¹³
    -0.08
    illance
    -0.08
    ÑĨо
    -0.08
    OperationException
    -0.07
    lection
    -0.07
    POSITIVE LOGITS
    ized
    0.12
    aceous
    0.10
    ated
    0.09
    ÙĬØ©
    0.09
    avig
    0.08
    wort
    0.08
    aires
    0.08
    iated
    0.08
    nelle
    0.08
    ica
    0.08
    Activations Density 0.011%

    No Known Activations