© 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. 19053
    Prev
    Next
    INDEX
    Explanations

    number or size

    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
    å°
    -0.06
    å½ĵ家
    -0.05
    ndo
    -0.05
    лкÑĥ
    -0.05
    å¯
    -0.05
    онаÑĤ
    -0.05
     Ùħاد
    -0.05
    æ¯ĶèµĽä¸Ń
    -0.05
    ieger
    -0.05
     indefinitely
    -0.05
    POSITIVE LOGITS
    çħŀ
    0.06
    亲åĴĮ
    0.06
    ichten
    0.05
    atele
    0.05
    è¿ĩæĿ¥
    0.05
    ocie
    0.05
     cerc
    0.05
    agir
    0.05
     keyed
    0.05
    ê²ł
    0.05
    Activations Density 0.023%

    No Known Activations