© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22392
    Prev
    Next
    INDEX
    Explanations

    entering or arriving somewhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    çĻ¾å§ĵ
    -0.06
    contact
    -0.06
    æݥ触
    -0.06
     contact
    -0.06
     Contact
    -0.06
    å¸Ĥæ°ij
    -0.05
    çĭ
    -0.05
    Contact
    -0.05
    gn
    -0.05
    èĢIJä¹ħ
    -0.05
    POSITIVE LOGITS
    веÑĢÑĪенÑģÑĤво
    0.06
     Everywhere
    0.06
    ä¸Ģåİħ
    0.06
    åħĴ
    0.06
    æħµ
    0.06
     ("-
    0.06
    rud
    0.06
    kek
    0.06
    èµĬ
    0.06
     Adolescent
    0.06
    Activations Density 0.002%

    No Known Activations