© 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. 20545
    Prev
    Next
    INDEX
    Explanations

    code segment specific character

    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
    éĴ©
    -0.05
    ä¹ĭæīĢ以
    -0.05
    ouri
    -0.05
     mans
    -0.05
     pand
    -0.05
    heck
    -0.05
     hook
    -0.05
    èĬ¦
    -0.04
     ->
    -0.04
    pel
    -0.04
    POSITIVE LOGITS
    ä¸ļçļĦ
    0.07
    å¾·åįİ
    0.06
    ará
    0.06
    vast
    0.06
    ائ
    0.06
    bero
    0.06
    æīĢæĮĩ
    0.06
    å¡ģ
    0.06
    ingu
    0.06
     miser
    0.06
    Activations Density 0.007%

    No Known Activations