© 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. 4659
    Prev
    Next
    INDEX
    Explanations

    will be / ’ll be

    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
    è´
    -0.12
    å¾ģ
    -0.10
    åĺ»
    -0.10
    å¦ĸ
    -0.09
    å¼łæī¬
    -0.09
     Tits
    -0.09
    bris
    -0.09
    OTE
    -0.09
    æĸ¼æĺ¯
    -0.09
    éĢŀ
    -0.08
    POSITIVE LOGITS
    бо
    0.09
    amo
    0.09
    å°±çŁ¥éģĵ
    0.08
    äºļåĨĽ
    0.08
    id
    0.08
    éŨåīį
    0.08
    çħ¦
    0.08
     Gabriel
    0.07
     ens
    0.07
    âĨĵ
    0.07
    Activations Density 0.041%

    No Known Activations