© 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. 6997
    Prev
    Next
    INDEX
    Explanations

    loss of job, license, or seat

    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
    åİĮ
    -0.08
    çŀ»
    -0.08
    pull
    -0.08
    é¢ī
    -0.08
    æŁĶ
    -0.08
    ardy
    -0.08
    ote
    -0.08
     humanoid
    -0.08
    ä½ĵè´´
    -0.08
     Rail
    -0.07
    POSITIVE LOGITS
    çĶļèĩ³
    0.12
    èµĸ以çĶŁåŃĺ
    0.11
    åħ¨éĥ¨
    0.11
    ä¹ĥèĩ³
    0.10
    éĺµåľ°
    0.10
    èµĦæł¼
    0.10
    çĶļèĩ³æĺ¯
    0.10
    ä¸ĢåĪĩ
    0.10
    éªij士
    0.09
    åıĤ
    0.09
    Activations Density 0.029%

    No Known Activations