© 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. 19317
    Prev
    Next
    INDEX
    Explanations

    Hey guys, Hey

    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
    otto
    -0.08
    çĴIJ
    -0.07
     lagi
    -0.07
     altr
    -0.07
    .asp
    -0.06
    OTOS
    -0.06
    表çİ°å½¢å¼ı
    -0.06
    owo
    -0.06
    å¦ĻçļĦ
    -0.06
    Ñģен
    -0.06
    POSITIVE LOGITS
    ding
    0.05
    令
    0.05
    äºĨæķ´ä¸ª
    0.05
     (
    0.05
    ix
    0.05
     mar
    0.05
    èĩ³æŀģ
    0.04
    对被
    0.04
     y
    0.04
     u
    0.04
    Activations Density 0.005%

    No Known Activations