© 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. 9631
    Prev
    Next
    INDEX
    Explanations

    the `an` or `on` sequence

    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
     pits
    -0.07
    habil
    -0.06
    äºĨä¸Ģé¢Ĺ
    -0.06
     convo
    -0.06
    åį¤
    -0.06
    tm
    -0.06
    çŃł
    -0.06
     pit
    -0.06
    åģļçļĦ
    -0.06
    æŀ¶è®¾
    -0.06
    POSITIVE LOGITS
    å½¢ãģ§
    0.08
    omm
    0.08
    ustus
    0.08
    geg
    0.08
    rung
    0.07
    heil
    0.07
    æĶ¾çŁ¢
    0.07
    ikit
    0.07
     Jennings
    0.07
    å¸ħæ°ĶçļĦ
    0.07
    Activations Density 1.722%

    No Known Activations