© 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. 20347
    Prev
    Next
    INDEX
    Explanations

    fire

    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
    oux
    -0.06
    éĢłæĪIJ伤害
    -0.06
    家ä¼Ļ
    -0.06
    isset
    -0.06
    viel
    -0.06
    amana
    -0.06
    ANK
    -0.05
    vall
    -0.05
    innt
    -0.05
    erset
    -0.05
    POSITIVE LOGITS
    ÙIJÙij
    0.06
    ebra
    0.06
    assis
    0.05
    modity
    0.05
    ä»»èģĮ
    0.05
    abetic
    0.05
    è§Ħ模
    0.05
     megb
    0.05
     Longer
    0.05
    åij¨è½¬
    0.05
    Activations Density 0.001%

    No Known Activations