© 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. 1568
    Prev
    Next
    INDEX
    Explanations

    for

    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¸Ģ件äºĭ
    -0.10
    borg
    -0.09
    dent
    -0.09
    ding
    -0.09
    éĹ²
    -0.09
    ToBounds
    -0.08
     Kron
    -0.08
    çĶļ
    -0.08
    è´¶
    -0.08
    åĵij
    -0.08
    POSITIVE LOGITS
     for
    0.24
     bagi
    0.22
    对äºİ
    0.22
     длÑı
    0.21
    สำ
    0.20
     dla
    0.19
    for
    0.18
     für
    0.18
    	for
    0.17
     باÙĦÙĨسبة
    0.17
    Activations Density 0.442%

    No Known Activations