© 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. 11382
    Prev
    Next
    INDEX
    Explanations

    cushion or Buckley

    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
    æ½ĩæ´Ĵ
    -0.11
    åįĥåı¤
    -0.10
    orno
    -0.09
    ackage
    -0.08
    æ¸ħæ¾Ī
    -0.08
    强æĤį
    -0.08
    acious
    -0.08
    èĪIJ
    -0.08
    acity
    -0.08
    usion
    -0.08
    POSITIVE LOGITS
    amel
    0.12
    edList
    0.10
    ably
    0.10
    å¹Ħ
    0.10
    çĦ¶æĺ¯
    0.10
    ingly
    0.10
    ary
    0.09
    å¸Ľ
    0.09
    ĩ
    0.09
    edReader
    0.09
    Activations Density 0.004%

    No Known Activations