© 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. 2776
    Prev
    Next
    INDEX
    Explanations

    may followed by different words

    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
    ivy
    -0.10
    agem
    -0.09
     Bundy
    -0.09
    swith
    -0.09
    å½ĵäºĭ
    -0.08
    éĥ½çŁ¥éģĵ
    -0.08
    ueur
    -0.08
    sat
    -0.08
    agn
    -0.08
    unity
    -0.08
    POSITIVE LOGITS
     mắn
    0.15
    ä¹Łåı¯èĥ½
    0.10
    bourne
    0.09
    -être
    0.09
    nard
    0.09
    æŃ£åĽłä¸º
    0.09
    ös
    0.09
    åĪĹ为
    0.08
    fair
    0.08
    fully
    0.08
    Activations Density 0.019%

    No Known Activations