© 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. 21945
    Prev
    Next
    INDEX
    Explanations

    conceived, conception, conceive

    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
    aru
    -0.09
    à¹īà¸Ńà¸ĩ
    -0.09
     thiá»ĥu
    -0.08
    ย
    -0.08
    adar
    -0.08
     constexpr
    -0.08
    çģ¾éļ¾
    -0.08
    ards
    -0.08
    ifle
    -0.08
    wood
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.10
    ä¸Ģ个éĹ®é¢ĺ
    0.10
    ption
    0.10
    pcion
    0.10
    å·²ä¹ħ
    0.10
    OrUpdate
    0.10
    æ£Ģå¯Łå®ĺ
    0.09
     notions
    0.09
    å²ĺ
    0.09
    弯
    0.09
    Activations Density 0.017%

    No Known Activations