© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5369
    Prev
    Next
    INDEX
    Explanations

    family members and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    çļ¿
    -0.10
    è¹Ļ
    -0.09
    ãģĦãģ¤
    -0.09
    anguage
    -0.09
     Ashe
    -0.09
    é³ħ
    -0.09
    åĸĻ
    -0.09
    zar
    -0.09
    oden
    -0.09
    owa
    -0.08
    POSITIVE LOGITS
    ening
    0.12
    ie
    0.12
    ened
    0.10
    åĴIJ
    0.10
    orary
    0.10
    ish
    0.09
    ees
    0.09
    ÙĪØ®
    0.09
    spir
    0.09
    esy
    0.09
    Activations Density 0.007%

    No Known Activations