© 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. 980
    Prev
    Next
    INDEX
    Explanations

    album titles or software titles

    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
    好似
    -0.09
    urat
    -0.09
    åѦä¸ļ
    -0.09
    æ¾³
    -0.08
     Flames
    -0.08
    ogh
    -0.08
    oving
    -0.08
    çģ«çĦ°
    -0.08
    èݲèĬ±
    -0.08
    娱
    -0.08
    POSITIVE LOGITS
    寮
    0.10
    Ñħи
    0.09
    裤
    0.09
    æĮij
    0.09
     наÑģÑĤоÑı
    0.09
     влад
    0.08
    游åĩ»éĺŁ
    0.08
    è¢ģ
    0.08
    溪
    0.08
    èĩªè¡Į车
    0.08
    Activations Density 0.106%

    No Known Activations