© 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. 21386
    Prev
    Next
    INDEX
    Explanations

    quantities and currency

    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
    hw
    -0.07
    æĹłå¤Ħ
    -0.07
    aha
    -0.06
    uda
    -0.06
    ئÙħ
    -0.06
    æµģè¿ŀ
    -0.06
    çıį
    -0.06
    anch
    -0.06
    urig
    -0.05
    æĹłä¸Ģ
    -0.05
    POSITIVE LOGITS
    客ä½ĵ
    0.06
    eiro
    0.06
    brate
    0.06
    第ä¸īæľŁ
    0.05
    íĨłë¦¬
    0.05
    æľºå¯Ĩ
    0.05
    ä¸įæĺİ
    0.05
    оÑģÑģ
    0.05
    osal
    0.05
    éné
    0.05
    Activations Density 0.044%

    No Known Activations