© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51618
    Prev
    Next
    INDEX
    Explanations

    forgotten or lost things

    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
    èĩ´åĬĽäºİ
    -0.09
    羡
    -0.09
    åµĬ
    -0.09
    åĬĽæ±Ĥ
    -0.09
    .Exists
    -0.09
    Dispatch
    -0.09
    çķ´
    -0.09
     заÑıв
    -0.09
    æıIJçİ°
    -0.08
    antas
    -0.08
    POSITIVE LOGITS
    éģĹ
    0.12
    éļıçĿĢæŶéĹ´
    0.12
    ä¹ħ
    0.11
    轶
    0.11
    æŶéļĶ
    0.11
    éģĹå¿ĺ
    0.11
    æ¹®
    0.11
    åĽŀæĥ³
    0.10
     Forgotten
    0.10
    éģĹ产
    0.10
    Activations Density 0.209%

    No Known Activations