© 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. 20551
    Prev
    Next
    INDEX
    Explanations

    live human

    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
    åħ¬æīĢ
    -0.06
    ਿà¨Ĩ
    -0.06
    kaz
    -0.06
    ectar
    -0.05
    integra
    -0.05
    ä¸IJ
    -0.05
    fits
    -0.05
    unn
    -0.05
    der
    -0.05
    ufs
    -0.05
    POSITIVE LOGITS
    èĥ¡æ¡ĥ
    0.06
     Twin
    0.05
    à¸Ħà¸Ńà¸Ļ
    0.05
    éĩijåĪļ
    0.05
     responders
    0.05
    arend
    0.05
    ropic
    0.05
    umps
    0.05
    æŁĶ
    0.05
    fru
    0.05
    Activations Density 0.012%

    No Known Activations