© 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. 17293
    Prev
    Next
    INDEX
    Explanations

    married status and family

    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
    åĹ£
    -0.09
    èĩªçĦ¶èĢĮ
    -0.08
    庶
    -0.08
    æİĩ
    -0.08
     Ðĵлав
    -0.08
     Sk
    -0.08
    大èĤ¡ä¸ľ
    -0.08
    vard
    -0.08
    pute
    -0.08
    诱
    -0.08
    POSITIVE LOGITS
    ly
    0.10
    allel
    0.09
    大åĬĽåıijå±ķ
    0.09
    ialog
    0.09
    çĤĢ
    0.09
    ness
    0.09
    /downloads
    0.09
    pedia
    0.09
    éļ¶å±ŀ
    0.09
    uration
    0.09
    Activations Density 0.010%

    No Known Activations