© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56905
    Prev
    Next
    INDEX
    Explanations

    time and areas

    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
     intimate
    -0.06
     compos
    -0.06
    åħ·
    -0.06
    åºĵéĩĮ
    -0.06
    -0.06
    stieg
    -0.06
    è¿Ļå¥Ĺ
    -0.06
     integral
    -0.05
    à¹Ģรืà¹Īà¸Ńà¸ĩ
    -0.05
     something
    -0.05
    POSITIVE LOGITS
    onso
    0.08
    onsin
    0.08
    gaard
    0.08
    ibun
    0.08
    innie
    0.08
    ddit
    0.08
    ëł¹
    0.08
    senz
    0.08
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.07
    olist
    0.07
    Activations Density 0.001%

    No Known Activations