© 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. 64345
    Prev
    Next
    INDEX
    Explanations

    repeated actions or duplicates

    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
    ìłĪ
    -0.08
    ÏĢη
    -0.07
    ritable
    -0.07
    chsel
    -0.07
    -python
    -0.07
    angler
    -0.07
    便è¦ģ
    -0.07
    è¢
    -0.07
    ILON
    -0.07
    пÑı
    -0.07
    POSITIVE LOGITS
     reinforcing
    0.09
     redundant
    0.08
     reinforce
    0.08
     reinforces
    0.08
    强åĮĸäºĨ
    0.07
     reinforcement
    0.07
    ä¸įå¿ħ
    0.07
     reinforced
    0.07
    uff
    0.07
    强åĮĸ
    0.07
    Activations Density 0.027%

    No Known Activations