© 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. 31818
    Prev
    Next
    INDEX
    Explanations

    pairwise connections

    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
    oyo
    -0.08
    ëł¹
    -0.08
    .squeeze
    -0.07
    å½ĵ头
    -0.07
     Gro
    -0.07
    leve
    -0.06
     differentiated
    -0.06
    rite
    -0.06
    ilig
    -0.06
    /opt
    -0.06
    POSITIVE LOGITS
     pairs
    0.11
     pairwise
    0.10
    pairs
    0.10
    Pairs
    0.09
     pair
    0.09
    .pair
    0.09
    pair
    0.08
    _pairs
    0.08
    Pair
    0.07
    ãĥļãĤ¢
    0.07
    Activations Density 0.015%

    No Known Activations