© 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. 18232
    Prev
    Next
    INDEX
    Explanations

    fluorescent bulbs, coffee, cola

    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
    igte
    -0.06
    cha
    -0.06
    amble
    -0.06
    æīįè¡Į
    -0.06
     handic
    -0.05
    _MISC
    -0.05
    åħīæĺ¯
    -0.05
    tem
    -0.05
     Bras
    -0.05
    esty
    -0.05
    POSITIVE LOGITS
    asion
    0.07
    彫
    0.06
    alloc
    0.05
    ç¡®åĪĩ
    0.05
    ador
    0.05
    AFF
    0.05
    deliver
    0.05
    uggy
    0.05
     khe
    0.05
     tượng
    0.05
    Activations Density 0.052%

    No Known Activations