© 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. 52328
    Prev
    Next
    INDEX
    Explanations

    web addresses and news titles

    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
    çĽ¸äº²
    -0.09
    ç£Ķ
    -0.08
    nearest
    -0.08
    å¾®éĩı
    -0.08
    èĥ¶
    -0.08
    çĶĺèĤĥçľģ
    -0.08
    åħ°å·ŀ
    -0.08
    æ¢Ĩ
    -0.08
    çłĶåıijæĬķåħ¥
    -0.08
    å¦ĩ
    -0.08
    POSITIVE LOGITS
    Backing
    0.10
    ä½łä¹Ł
    0.10
    磫
    0.10
    èѦæĥķ
    0.09
    èŀ³
    0.09
    ãĥĿãĥ³
    0.09
    çľĭæ³ķ
    0.09
    igr
    0.09
    é»į
    0.09
    pond
    0.08
    Activations Density 0.049%

    No Known Activations