© 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. 25026
    Prev
    Next
    INDEX
    Explanations

    identity or zero

    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
     heated
    -0.07
    Ñĥди
    -0.06
    ache
    -0.06
    éļħ
    -0.06
    -turned
    -0.06
    ![
    -0.06
    falt
    -0.06
    ×ķ׾×Ļ
    -0.06
     keyed
    -0.06
    òng
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ľà¸¥à¹Īา
    0.08
    ceau
    0.07
    arel
    0.07
    ÅĨa
    0.07
    emaker
    0.07
    cest
    0.07
    æĺķ
    0.07
    atorie
    0.07
    emis
    0.07
    æīĢ以对
    0.07
    Activations Density 0.002%

    No Known Activations