© 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. 23413
    Prev
    Next
    INDEX
    Explanations

    directional corners

    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
    rell
    -0.07
    ily
    -0.07
    ä¹ħèĢĮ
    -0.07
    z
    -0.07
    yle
    -0.07
    ihan
    -0.06
    assi
    -0.06
    ÙĨاÙħÙĩ
    -0.06
    æŨ
    -0.06
    isi
    -0.06
    POSITIVE LOGITS
     corner
    0.10
    hoek
    0.09
    corner
    0.09
    Corner
    0.09
     corners
    0.08
    éļĪ
    0.08
    -corner
    0.08
    çŃīå¤Ħ
    0.08
    indung
    0.08
    een
    0.08
    Activations Density 0.023%

    No Known Activations