© 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. 64573
    Prev
    Next
    INDEX
    Explanations

    singularities, product, Field, tenderness, Aziz

    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
    antar
    -0.07
    angkan
    -0.07
    éij«
    -0.07
    Stride
    -0.07
     Beverage
    -0.07
     recip
    -0.07
    rawn
    -0.07
     availability
    -0.07
    _advance
    -0.07
    olland
    -0.07
    POSITIVE LOGITS
    ä¸Ģå¤Ħ
    0.08
    çĤ¹çļĦ
    0.08
     smooth
    0.08
     points
    0.08
    udas
    0.08
    æĦĪåIJĪ
    0.08
    å¹³æ»ij
    0.08
    两å¤Ħ
    0.08
    åıijçĶŁæŶ
    0.08
    éĽĨä¸Ńåľ¨
    0.08
    Activations Density 0.004%

    No Known Activations