© 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. 21753
    Prev
    Next
    INDEX
    Explanations

    mobile app development

    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
    æ±ĩ
    -0.10
    æĦł
    -0.10
    éħį
    -0.10
    失
    -0.10
    bsd
    -0.09
    éľı
    -0.09
    临
    -0.09
    èģĶ
    -0.09
    remote
    -0.09
     Cotton
    -0.09
    POSITIVE LOGITS
    å´¤
    0.10
    åĩ¹
    0.09
    èŀŃ
    0.09
    åĬ¨åijĺ
    0.09
    ket
    0.09
    FML
    0.09
    èĥ´
    0.08
    .getSharedPreferences
    0.08
    è¿
    0.08
     ket
    0.08
    Activations Density 0.228%

    No Known Activations