© 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. 50682
    Prev
    Next
    INDEX
    Explanations

    leaders' names

    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
    æij©æĵ¦
    -0.09
    illet
    -0.09
     vuel
    -0.09
    楹
    -0.09
    å®īçĦ¶
    -0.08
    ä¼İ
    -0.08
    ãģĵãģĿ
    -0.08
    è¡ĮæĶ¿å®¡æī¹
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    éĺij
    -0.08
    POSITIVE LOGITS
    èĹĵ
    0.10
    urf
    0.10
    说è¿ĩ
    0.09
    çħ¦
    0.09
    çĶ
    0.09
    amen
    0.09
    ople
    0.08
    ðŁı»
    0.08
    è²ĺ
    0.08
    rgan
    0.08
    Activations Density 0.006%

    No Known Activations