© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2401
    Prev
    Next
    INDEX
    Explanations

    inland, moist air, cities modify

    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
    éĢĢåĽŀ
    -0.10
     اÙĦÙĪاØŃد
    -0.09
    ç¾Ĭæ¯Ľ
    -0.09
    åıĶ
    -0.08
    èµĽ
    -0.08
    uda
    -0.08
    åħīåѦ
    -0.08
    <<
    -0.08
    åĸľ
    -0.08
    毽
    -0.08
    POSITIVE LOGITS
    çĽIJ
    0.11
    ä¸Ģä½ĵåĮĸ
    0.10
    æ±ł
    0.10
    æł¡åĽŃ
    0.10
     Salt
    0.09
    æļ´
    0.09
     cleric
    0.09
    åĵº
    0.09
    _salt
    0.09
     mojo
    0.08
    Activations Density 0.040%

    No Known Activations