© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19501
    Prev
    Next
    INDEX
    Explanations

    permission

    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
    rophy
    -0.08
    hund
    -0.07
    bove
    -0.07
    apé
    -0.07
    Cancelable
    -0.07
    اجة
    -0.07
    guer
    -0.07
    ower
    -0.06
    variably
    -0.06
    éĻIJäºİ
    -0.06
    POSITIVE LOGITS
    ew
    0.07
    ÙĨØŃÙĨ
    0.06
    ed
    0.06
    ÑĮÑİ
    0.05
    eds
    0.05
    milyen
    0.05
    ner
    0.05
    nal
    0.05
    zeitig
    0.05
    ä¹ī
    0.05
    Activations Density 0.011%

    No Known Activations