© 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. 19946
    Prev
    Next
    INDEX
    Explanations

    action verbs

    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
    utzer
    -0.06
    [âĢ¦
    -0.06
    CMP
    -0.05
    ÙĪبة
    -0.05
    utki
    -0.05
    imonio
    -0.05
    ëĭµ
    -0.05
    ucin
    -0.05
     misc
    -0.05
    [âĢ¦]
    -0.05
    POSITIVE LOGITS
    罪éŃģ
    0.05
     clit
    0.05
    ila
    0.05
    æĿ¯
    0.05
     &'
    0.05
    eceÄŁ
    0.05
    ile
    0.05
    她们
    0.05
    ale
    0.05
     apar
    0.05
    Activations Density 0.027%

    No Known Activations