© 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. 8074
    Prev
    Next
    INDEX
    Explanations

    substitution / substitute

    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
    elige
    -0.09
    ighted
    -0.08
    ening
    -0.08
    itage
    -0.08
    urie
    -0.08
    liest
    -0.08
    liness
    -0.08
    stens
    -0.08
    itorial
    -0.08
    ugin
    -0.07
    POSITIVE LOGITS
    ively
    0.09
    aneous
    0.08
    ary
    0.07
    ات
    0.07
    /add
    0.07
    Into
    0.07
     Äijá»ķi
    0.07
    /rem
    0.07
    Ø®
    0.07
     into
    0.06
    Activations Density 0.010%

    No Known Activations