© 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. 18907
    Prev
    Next
    INDEX
    Explanations

    ftp client, zip file

    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
     dá»Ŀi
    -0.06
    kamp
    -0.06
    ówczas
    -0.06
     souci
    -0.06
    åīªè£ģ
    -0.06
     morceau
    -0.06
    ç»ĵæĿŁä¹ĭåIJİ
    -0.06
    arp
    -0.06
    轩
    -0.06
    è´¹å°Ķ
    -0.06
    POSITIVE LOGITS
    åĬĽåĴĮ
    0.05
    voz
    0.05
    æIJŃ
    0.05
    ä¹ī
    0.05
    agam
    0.05
    åĬŁ
    0.05
    put
    0.05
    ä¹īçļĦ
    0.05
    说
    0.05
    è´¡
    0.05
    Activations Density 0.002%

    No Known Activations