© 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. 31640
    Prev
    Next
    INDEX
    Explanations

    writing to someone or something

    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
     briefed
    -0.09
    æľĢåIJİä¸Ģ次
    -0.09
    è¾ĩ
    -0.08
     colleague
    -0.08
    ever
    -0.08
     Contemporary
    -0.08
    arrass
    -0.08
    æİ¥åıĹäºĨ
    -0.08
    ifr
    -0.08
    .addRow
    -0.08
    POSITIVE LOGITS
    atcher
    0.10
    æĶ¶
    0.09
    BEST
    0.09
    为ä¹ĭ
    0.09
    ä¸įæŃ»
    0.09
    湿润
    0.09
    ENCE
    0.09
    æĥ³çŁ¥éģĵ
    0.09
    éĻį温
    0.09
    产åĵģè´¨éĩı
    0.08
    Activations Density 0.035%

    No Known Activations