© 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. 20134
    Prev
    Next
    INDEX
    Explanations

    the absence

    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
    ecen
    -0.07
    eel
    -0.07
    ehr
    -0.07
    cust
    -0.07
    blo
    -0.07
    ש×Ļ×Ŀ
    -0.07
    elÅij
    -0.07
    ä¹±
    -0.07
    æº
    -0.07
    UCK
    -0.07
    POSITIVE LOGITS
    èĭ¥èĥ½
    0.07
    /fixtures
    0.07
     olev
    0.06
    çĻ½çİī
    0.06
     suggested
    0.06
    [in
    0.06
     ability
    0.06
    åĩºèµ°
    0.06
     Oto
    0.06
    åĬªåĬĽåģļåĪ°
    0.06
    Activations Density 0.276%

    No Known Activations