© 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. 19308
    Prev
    Next
    INDEX
    Explanations

    hired by mercenaries

    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
     Agung
    -0.06
     unified
    -0.06
    aily
    -0.05
    -sama
    -0.05
    åħ¥èģĮ
    -0.05
     par
    -0.05
    tijd
    -0.05
    ê°ģ
    -0.05
    unity
    -0.05
     shared
    -0.05
    POSITIVE LOGITS
     recons
    0.07
    èī
    0.06
    è´©
    0.05
    æŁ»
    0.05
     sublicense
    0.05
    åĽŀäºĭ
    0.05
    è¿ĻäºĽéĹ®é¢ĺ
    0.05
    orrent
    0.05
     exhaus
    0.05
    èĤ
    0.05
    Activations Density 0.008%

    No Known Activations