© 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. 51614
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    èĻĶ
    -0.09
    åİŁåĪĻä¸Ĭ
    -0.09
    è°ħ解
    -0.09
    åīį线
    -0.08
     Attribution
    -0.08
    à¹ģà¸Ķà¸Ļ
    -0.08
    _counters
    -0.08
     Memo
    -0.08
     despair
    -0.08
    å®ŀçĶ¨æĢ§
    -0.08
    POSITIVE LOGITS
    éģ¿åħį
    0.11
    以åħį
    0.10
    è¶Ĭ好
    0.10
    æľªå¿ħ
    0.10
    访
    0.09
    èĩªæľī
    0.09
    åĿıäºĭ
    0.09
    &type
    0.08
    äºĨ好
    0.08
    让å®ĥ
    0.08
    Activations Density 0.036%

    No Known Activations