© 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. 20424
    Prev
    Next
    INDEX
    Explanations

    on or up

    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
    ä¸įæĺİ
    -0.12
    æĶ¶è´¹æłĩåĩĨ
    -0.09
    è¿Ļ件äºĭæĥħ
    -0.09
    .Unity
    -0.09
    _DEST
    -0.09
     suprem
    -0.09
    .destination
    -0.09
     Curt
    -0.09
    akra
    -0.09
    astos
    -0.09
    POSITIVE LOGITS
    .tc
    0.09
    7
    0.08
    åĪĢ
    0.08
    人éĹ´
    0.08
     yaÅŁan
    0.08
    plies
    0.08
    8
    0.08
    aned
    0.08
    èµİ
    0.08
    å»īä»·
    0.08
    Activations Density 0.010%

    No Known Activations