© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50697
    Prev
    Next
    INDEX
    Explanations

    goodies or Goodman

    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
    åģıåģı
    -0.09
    å®ļäºĨ
    -0.08
    åıĬåħ¶ä»ĸ
    -0.08
    ÑģÑģ
    -0.08
    pare
    -0.08
    overs
    -0.08
    Fixture
    -0.08
    åį«çĶŁåģ¥åº·
    -0.08
    iper
    -0.08
    sWith
    -0.08
    POSITIVE LOGITS
    é½IJåħ¨
    0.12
    енÑĮк
    0.10
    amber
    0.10
    geb
    0.09
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.09
    è¢ĭ
    0.09
    ente
    0.09
    åĪ¸
    0.09
    æģĥ
    0.09
    åħ®
    0.09
    Activations Density 0.004%

    No Known Activations