© 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. 30654
    Prev
    Next
    INDEX
    Explanations

    relationship or dating

    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
    èĢģæŧ
    -0.11
     thông
    -0.09
    对æĸ¹
    -0.09
    ITAL
    -0.09
    é«
    -0.08
    éģIJ
    -0.08
    OfWork
    -0.08
    æį¢
    -0.08
    rans
    -0.08
    éľŀ
    -0.08
    POSITIVE LOGITS
    ä¹ĭæĥħ
    0.12
    æĦŁæĥħ
    0.11
    æģĭæĥħ
    0.11
    å¸ĪçĶŁ
    0.10
    ä¾Ľæ±Ĥ
    0.10
    åįĩ温
    0.10
    æļ§æĺ§
    0.09
    ä»ĬçĶŁ
    0.09
    çºł
    0.09
    çļĦæĦŁæĥħ
    0.09
    Activations Density 0.055%

    No Known Activations