© 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. 20469
    Prev
    Next
    INDEX
    Explanations

    consequences and outcomes

    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
     powered
    -0.07
    aufen
    -0.06
    ç¾İ好çļĦæľªæĿ¥
    -0.06
    dense
    -0.06
    è¿ŀç»Ń
    -0.06
    åľ¨æľªæĿ¥
    -0.06
    åľ¨æľªæĿ¥çļĦ
    -0.05
    plans
    -0.05
    ajes
    -0.05
     alınan
    -0.05
    POSITIVE LOGITS
    äºķçĦ¶
    0.05
    iasm
    0.05
     cant
    0.05
    ivu
    0.05
    å°½
    0.05
    esion
    0.05
    sofar
    0.05
    acre
    0.05
    顺便
    0.05
    åĴĮå¹³
    0.05
    Activations Density 0.043%

    No Known Activations