© 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. 20747
    Prev
    Next
    INDEX
    Explanations

    email input fields

    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
    klen
    -0.07
     intr
    -0.07
     opa
    -0.06
    /operator
    -0.06
    intr
    -0.06
    abu
    -0.06
    ogan
    -0.06
     ratt
    -0.06
    æĬ¥ä¸ļ
    -0.06
    jian
    -0.06
    POSITIVE LOGITS
    iÄį
    0.06
    icales
    0.05
    åıªæ±Ĥ
    0.05
    ç®ĩ
    0.05
     hern
    0.05
    çģĺ
    0.05
     sink
    0.05
    itations
    0.05
    çļĦåĶ¯ä¸Ģ
    0.05
     naw
    0.05
    Activations Density 0.013%

    No Known Activations