© 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. 41471
    Prev
    Next
    INDEX
    Explanations

    exclusion, elimination, narrow, reject

    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
    ackson
    -0.08
    aml
    -0.07
    lite
    -0.07
    actly
    -0.07
    éĢģæĿ¥
    -0.07
    ieu
    -0.07
    æī¹
    -0.07
    anne
    -0.07
    elt
    -0.07
    ennifer
    -0.07
    POSITIVE LOGITS
    äºĨä¸ĢåĪĩ
    0.07
    ools
    0.06
    ä½łäºĨ
    0.06
    leme
    0.06
    ä¸įå¿ħè¦ģçļĦ
    0.06
    жиÑĤеÑģÑĮ
    0.06
    à¸ģัà¸Ļà¹Ħà¸Ľ
    0.06
    ãģĹãĤĤ
    0.06
    istol
    0.06
    å½ĵãģ¦
    0.06
    Activations Density 0.002%

    No Known Activations