© 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. 17489
    Prev
    Next
    INDEX
    Explanations

    product rule and composition

    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
    åıijå±ķè¶ĭåĬ¿
    -0.06
    มà¸Ļ
    -0.06
    åĿĩè¡¡åıijå±ķ
    -0.06
    åıijå±ķ缮æłĩ
    -0.06
    çļĦéĴ±
    -0.05
    æĹ¥çĶ¨çĻ¾è´§
    -0.05
    åºŁè¯Ŀ
    -0.05
    æ´Ľæĸ¯
    -0.05
    icha
    -0.05
    hort
    -0.05
    POSITIVE LOGITS
    invert
    0.05
    wrapper
    0.05
    edio
    0.05
    åĬĪ
    0.05
     exc
    0.05
    oints
    0.05
     repmat
    0.05
    CKER
    0.05
    -transfer
    0.05
    anakan
    0.05
    Activations Density 0.052%

    No Known Activations