© 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. 39496
    Prev
    Next
    INDEX
    Explanations

    keep track of state

    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
    å®īåħ¨éĹ®é¢ĺ
    -0.08
    éĥ¨çº§
    -0.08
    elh
    -0.08
    eya
    -0.08
    amah
    -0.08
    ey
    -0.07
    endah
    -0.07
     RequestMethod
    -0.07
    ehl
    -0.07
    eve
    -0.07
    POSITIVE LOGITS
     list
    0.07
    IndexOf
    0.07
     separate
    0.07
     seperate
    0.07
    æĢ»çļĦ
    0.07
     semacam
    0.07
    rightness
    0.07
     separately
    0.07
    æĪijä¹Łæľī
    0.07
    åĪĹ表
    0.07
    Activations Density 0.042%

    No Known Activations