© 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. 22013
    Prev
    Next
    INDEX
    Explanations

    tell us how

    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
    æĹłæĥħ
    -0.09
    æĪijå¿ĥéĩĮ
    -0.09
    å¾ĹåĪ°
    -0.09
    æĪijèĩªå·±
    -0.09
    tap
    -0.09
    为ä»Ģä¹Īä¸į
    -0.09
     myself
    -0.09
    çīĮåŃIJ
    -0.09
    åĩĢåĢ¼
    -0.09
    æĪij们çİ°åľ¨
    -0.09
    POSITIVE LOGITS
    çļĦçľĭæ³ķ
    0.10
    ration
    0.10
    eld
    0.09
    inger
    0.09
    çĺ¦èº«
    0.09
    ä½
    0.09
     Rash
    0.08
    actus
    0.08
    çľĭæ³ķ
    0.08
    å¿Ĵ
    0.08
    Activations Density 0.010%

    No Known Activations