© 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. 20460
    Prev
    Next
    INDEX
    Explanations

    not sufficient or alone

    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
    æĻ®
    -0.06
    æŃ£å®Ĺ
    -0.06
    ohn
    -0.06
    羣æľī
    -0.05
    æĦıçļĦ
    -0.05
    itung
    -0.05
    æŀģ大çļĦ
    -0.05
    ä½ķåħ¶
    -0.05
    yl
    -0.05
    çļĦå®ŀéĻħ
    -0.05
    POSITIVE LOGITS
    ä¹Łå¿ħé¡»
    0.07
    ä¹ŁåºĶ该
    0.06
     neglected
    0.06
    lán
    0.06
    woff
    0.06
    èIJ©
    0.06
    åĢºåĪ¸ä¿¡æģ¯
    0.06
    å®īç½®
    0.06
     alone
    0.06
    ç»Ŀ对ä¸įèĥ½
    0.05
    Activations Density 0.011%

    No Known Activations