© 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. 19930
    Prev
    Next
    INDEX
    Explanations

    in addition to

    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
    æīĵç®Ĺ
    -0.06
    à¸Łà¸´à¸ģ
    -0.06
    ois
    -0.06
    arp
    -0.06
    èħ
    -0.06
    trag
    -0.06
    ÑģÑĤеÑģÑĤвенно
    -0.06
    æ§į
    -0.06
     Każ
    -0.06
    æŀª
    -0.06
    POSITIVE LOGITS
    å«£
    0.05
    ÑĢа
    0.05
    ériment
    0.05
    çĦī
    0.05
    matched
    0.05
    é¦ĸæŃĮ
    0.05
    emente
    0.05
     Th
    0.05
    acc
    0.05
    äºļäºİ
    0.05
    Activations Density 0.014%

    No Known Activations