© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19824
    Prev
    Next
    INDEX
    Explanations

    what happens

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -0.05
    éĿ¶
    -0.05
    лаг
    -0.05
     constit
    -0.05
    -
    -0.05
     :
    -0.05
     flat
    -0.05
    /
    -0.05
    æĪijçľģ
    -0.05
     plain
    -0.05
    POSITIVE LOGITS
    èµ°ä¸Ģèµ°
    0.07
    æĽ´ä½³
    0.07
    æĽ´å®īåħ¨
    0.07
    irão
    0.07
    åĬĽä½ľ
    0.07
    hirt
    0.07
    elv
    0.07
    åħ¶ä»ĸåľ°æĸ¹
    0.07
    æľīèĥ½åĬĽ
    0.07
    æŃ£ç¡®ä½¿çĶ¨
    0.06
    Activations Density 0.005%

    No Known Activations