© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17513
    Prev
    Next
    INDEX
    Explanations

    adding elements to collections

    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
    Referensi
    -0.07
    ücü
    -0.06
    apper
    -0.06
    使çĶ¨çļĦ
    -0.06
    é¢Ŀ
    -0.06
    arine
    -0.06
    amen
    -0.05
    enga
    -0.05
    باء
    -0.05
    emonic
    -0.05
    POSITIVE LOGITS
     whom
    0.05
    dach
    0.05
    ÑĦо
    0.05
    aturahmi
    0.05
    çĪ±è½¦
    0.05
    ä»ĸäºĨ
    0.05
    åĤĺ
    0.05
    keb
    0.05
    åı°åīį
    0.05
    DTD
    0.05
    Activations Density 0.004%

    No Known Activations