© 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. 34558
    Prev
    Next
    INDEX
    Explanations

    require c, great for, excited about

    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
    å¦Ĥä½ķçľĭå¾ħ
    -0.11
    ehr
    -0.10
    两年åīį
    -0.09
    ä¸įæĸŃæī©å¤§
    -0.09
    æĪIJ为ä¸Ģ个
    -0.09
    RAFT
    -0.09
    _ASSUME
    -0.09
    è´£
    -0.09
    alue
    -0.09
     Ñĩем
    -0.08
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.12
    å®ĥ们
    0.12
    éĢIJä¸Ģ
    0.09
    lops
    0.09
     either
    0.09
    åĪĨåĪ«æĺ¯
    0.09
     themselves
    0.09
     коÑĤоÑĢÑĭÑħ
    0.09
    åIJĦèĩª
    0.08
    ols
    0.08
    Activations Density 0.288%

    No Known Activations