© 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. 1771
    Prev
    Next
    INDEX
    Explanations

    grant announcement process

    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
     souvenir
    -0.10
    æİ°
    -0.09
    ä¸Ģä¸Ŀ
    -0.09
     wis
    -0.08
     dam
    -0.08
    迷失
    -0.08
    çī¹æĿĥ
    -0.08
    çī¹æ´¾
    -0.08
    dam
    -0.08
    è°Ĭ
    -0.08
    POSITIVE LOGITS
    æī¿
    0.13
    åį§
    0.10
    .managed
    0.10
    å¯ĵ
    0.09
    +xml
    0.09
     scram
    0.09
    czy
    0.09
    èµĺ
    0.09
    æľ¬ç§ij
    0.09
    å°±åĥı
    0.09
    Activations Density 0.103%

    No Known Activations