© 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. 5778
    Prev
    Next
    INDEX
    Explanations

    Army Corps

    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
    æµ·éĩı
    -0.10
    èµĺ
    -0.09
    åĩºè·¯
    -0.09
    çĤ¬
    -0.09
    å¾Ģè¿Ķ
    -0.09
     discre
    -0.09
    oya
    -0.08
    amus
    -0.08
    窳
    -0.08
    é£ı
    -0.08
    POSITIVE LOGITS
    åŁŃ
    0.09
    anager
    0.09
     Ñģамом
    0.08
     Brend
    0.08
    rot
    0.08
    plementary
    0.08
    åŃĹåı·
    0.08
    Europe
    0.08
    éķ¿æ±Ł
    0.08
    ÑħÑĢан
    0.08
    Activations Density 0.004%

    No Known Activations