© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51164
    Prev
    Next
    INDEX
    Explanations

    new

    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
    ç»ıæŁ¥
    -0.10
    amer
    -0.10
    åĿ³
    -0.10
    å§ĭ
    -0.09
     cannons
    -0.09
    abal
    -0.09
    nga
    -0.09
    è½°
    -0.09
    天涯
    -0.09
    æĹ®
    -0.09
    POSITIVE LOGITS
    æĥ¯
    0.09
    è¿ĩ
    0.09
    ish
    0.09
    -ish
    0.09
    éĢĤ度
    0.09
    åľ¨æѤ
    0.08
     functioning
    0.08
    oft
    0.08
     vs
    0.08
    æ¸ij
    0.07
    Activations Density 0.035%

    No Known Activations