© 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. 18367
    Prev
    Next
    INDEX
    Explanations

    buyer , attack , destinations , component

    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
    аÑĤелÑĮ
    -0.07
    饮
    -0.06
    ãĤ¤ãĤ¹
    -0.06
    mitt
    -0.06
    oucher
    -0.06
    å¿ĥèĥ¸
    -0.06
    otin
    -0.06
    оÑģÑĥ
    -0.06
    ok
    -0.06
    符åIJĪ
    -0.06
    POSITIVE LOGITS
    hoe
    0.06
    è¯ķåĽ¾
    0.05
    iller
    0.05
    çĪª
    0.05
    illers
    0.05
    è¹´
    0.05
    bia
    0.05
    ellular
    0.05
    izers
    0.05
    çĿĢ
    0.05
    Activations Density 0.086%

    No Known Activations