© 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. 8650
    Prev
    Next
    INDEX
    Explanations

    producer or stag

    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
    laÅŁ
    -0.10
    gether
    -0.09
    èļ£
    -0.09
    à¸ģารศึà¸ģษา
    -0.09
    iseau
    -0.08
    entifier
    -0.08
    ìŁģ
    -0.08
    çĶŁè¾ī
    -0.08
    ornings
    -0.07
    ì¦ĺ
    -0.07
    POSITIVE LOGITS
    bourne
    0.10
    apore
    0.09
    haft
    0.09
    ning
    0.08
    yani
    0.08
    æĩ¸åij½
    0.08
    à¸Ħà¹Į
    0.08
    werb
    0.08
    ifter
    0.08
    tlement
    0.08
    Activations Density 0.006%

    No Known Activations