© 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. 19049
    Prev
    Next
    INDEX
    Explanations

    wolf, wolves, werewolf

    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
    orp
    -0.06
    educt
    -0.06
     Airways
    -0.06
    dasar
    -0.06
    oby
    -0.05
    æ½Ń
    -0.05
    imenta
    -0.05
    eka
    -0.05
    air
    -0.05
    life
    -0.05
    POSITIVE LOGITS
    çĭ¼äºº
    0.06
    imb
    0.06
    alde
    0.06
    å·´åħĭ
    0.05
    漪
    0.05
     wolf
    0.05
    æīĵçł´äºĨ
    0.05
    èģĺ
    0.05
    à¹Ĥà¸Ħ
    0.05
    athom
    0.05
    Activations Density 0.009%

    No Known Activations