© 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. 56403
    Prev
    Next
    INDEX
    Explanations

    mental and emotional topics

    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
    мол
    -0.10
    pike
    -0.09
    sume
    -0.09
    outs
    -0.08
    -offset
    -0.08
    .retrieve
    -0.08
     ÑĢеж
    -0.08
    ALE
    -0.08
    _RESERVED
    -0.08
     Chu
    -0.08
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.13
    è°§
    0.09
     aspects
    0.09
    æĥħæĦŁ
    0.09
    çĥ¦èºģ
    0.09
    çĶŁæķĪ
    0.09
    åį¡æĭī
    0.09
    æĸ¹éĿ¢çļĦ
    0.09
    æģIJæħĮ
    0.09
     mood
    0.08
    Activations Density 0.417%

    No Known Activations