© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9511
    Prev
    Next
    INDEX
    Explanations

    raising children

    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
    çľ¼éĩĮ
    -0.10
     Starr
    -0.09
    éĩĩæļĸ
    -0.09
    ä»Ģä¹ĪæŶåĢĻ
    -0.09
    åŁ
    -0.09
     зÑĢ
    -0.09
    ç¬
    -0.09
    缨
    -0.09
    æĪijå¸ĮæľĽ
    -0.09
    æĥ³åİ»
    -0.08
    POSITIVE LOGITS
    plets
    0.09
    eln
    0.09
    ä¸Ģä¸ĸ
    0.08
    宣æī¬
    0.08
     McB
    0.08
    æ°ij主
    0.08
    TRL
    0.07
    æĽ·
    0.07
     corre
    0.07
    Bus
    0.07
    Activations Density 0.018%

    No Known Activations