© 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. 36348
    Prev
    Next
    INDEX
    Explanations

    work, job, occupational, manufacturing

    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
    erin
    -0.09
    èļ±
    -0.09
     tiny
    -0.08
    楸
    -0.08
    ä¸Ńåįİ
    -0.08
    å®ļä»·
    -0.08
    å¾ģ
    -0.08
    æ§Į
    -0.08
    ToFront
    -0.08
    Forum
    -0.07
    POSITIVE LOGITS
    åľ¨çİ°åľº
    0.10
     supervisors
    0.10
    åľ¨äº¬
    0.09
    ضØŃ
    0.09
    è·¨è¶Ĭ
    0.09
    å²Ĺä½į
    0.09
    iswa
    0.09
    quee
    0.09
     Türkçe
    0.09
    è¯Ħæ¯Ķ
    0.08
    Activations Density 0.063%

    No Known Activations