© 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. 18540
    Prev
    Next
    INDEX
    Explanations

    founding dates

    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
    .ev
    -0.05
    ظÙħ
    -0.05
    .om
    -0.05
     themselves
    -0.05
    estin
    -0.05
    åij³
    -0.05
    lej
    -0.05
    æ£Ģ
    -0.05
    è¶ħé«ĺ
    -0.05
     served
    -0.05
    POSITIVE LOGITS
    Ø·ÙĦا
    0.06
    è¿Ľç¨ĭ
    0.06
    è¿Ľç¨ĭä¸Ń
    0.06
    halte
    0.06
    åħ¬è®¤
    0.06
     efectiv
    0.06
    大æĶ¾
    0.06
    nation
    0.05
    isle
    0.05
     appropriated
    0.05
    Activations Density 0.019%

    No Known Activations