© 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. 13867
    Prev
    Next
    INDEX
    Explanations

    dating and trading sites

    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
    inger
    -0.07
    óle
    -0.07
    æѦèĢħ
    -0.07
    atura
    -0.06
     pani
    -0.06
    parallel
    -0.06
    elian
    -0.06
    iros
    -0.06
    à¸Ĺà¸Ńà¸Ķ
    -0.06
    enia
    -0.06
    POSITIVE LOGITS
    allet
    0.08
    protobuf
    0.08
    paro
    0.08
    erra
    0.07
    erral
    0.07
    ิà¹Īม
    0.07
    çĥ
    0.07
    æµĵæµĵçļĦ
    0.07
    azor
    0.07
    acks
    0.07
    Activations Density 0.030%

    No Known Activations