© 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. 21954
    Prev
    Next
    INDEX
    Explanations

    sales and related roles

    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
     mainstream
    -0.06
    arken
    -0.05
    aste
    -0.05
    æłĸ
    -0.05
     critique
    -0.05
    olith
    -0.05
    quake
    -0.05
     '<?
    -0.05
    ä¸ĢæľŁ
    -0.05
    rig
    -0.05
    POSITIVE LOGITS
    eson
    0.06
    sätze
    0.06
     Territory
    0.06
    OBO
    0.06
    é¢ĨåľŁ
    0.06
    è±ģ
    0.06
    éłĺ
    0.06
     Metropolitan
    0.06
    odia
    0.06
     Yad
    0.06
    Activations Density 0.019%

    No Known Activations