© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17932
    Prev
    Next
    INDEX
    Explanations

    java annotations

    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
    æĩĤçļĦ
    -0.05
    champ
    -0.05
     chuẩn
    -0.05
     standard
    -0.05
     specifications
    -0.05
    vara
    -0.05
    å®Įæķ´
    -0.05
    æĺ¾
    -0.05
    ORO
    -0.05
    afd
    -0.04
    POSITIVE LOGITS
    odor
    0.07
    ç«ĭãģ¦
    0.06
    intr
    0.06
    ä¸Ģä½ĵçļĦ
    0.06
    éħª
    0.06
     kaps
    0.06
    æĶ¾çŁ¢
    0.06
    游
    0.06
    ÑİÑĢ
    0.06
    并å¤Ħ
    0.06
    Activations Density 0.026%

    No Known Activations