© 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. 17156
    Prev
    Next
    INDEX
    Explanations

    being + adjective/past participle

    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
    Ñģп
    -0.06
    -death
    -0.05
     naked
    -0.05
    thing
    -0.05
    θε
    -0.05
    ikin
    -0.05
    ness
    -0.05
    menta
    -0.05
    åħ
    -0.05
    éĴ±çļĦ
    -0.05
    POSITIVE LOGITS
    en
    0.07
    ous
    0.07
    mend
    0.07
    ãĥ£ãĥ³
    0.07
    à¸ģวà¹Īา
    0.07
    prib
    0.07
    enj
    0.07
    tanda
    0.06
    agoza
    0.06
    ìĸ´
    0.06
    Activations Density 0.016%

    No Known Activations