© 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. 21009
    Prev
    Next
    INDEX
    Explanations

    examples like for instead cover

    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
     ↵↵
    -0.07
    z
    -0.06
    缸åħ³
    -0.06
    缸åħ³æĥħåĨµ
    -0.06
    çļĦä¸įèī¯
    -0.05
    æĭīéĵ¾
    -0.05
    zusch
    -0.05
    	↵↵
    -0.05
    åĴĮ缸åħ³
    -0.05
    缸åħ³ä¼ģä¸ļ
    -0.05
    POSITIVE LOGITS
    èĤ¯å®ļçļĦ
    0.05
    æĭĹ
    0.05
    soever
    0.05
    doÄŁan
    0.05
    ;(
    0.05
    ราà¸ĩ
    0.05
    à¹Īวม
    0.05
    onsor
    0.05
    ัà¸ļ
    0.05
    infile
    0.05
    Activations Density 0.017%

    No Known Activations