© 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. 9337
    Prev
    Next
    INDEX
    Explanations

    Gossip Girl, Kirby, Opry, Pig, office

    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
    ç»į
    -0.11
    å¹³æ°ij
    -0.09
    pcf
    -0.09
     Studios
    -0.09
    åģİ
    -0.08
    ç¿Ģ
    -0.08
     Parenthood
    -0.08
    çľģ级
    -0.08
    åIJ»
    -0.08
    leon
    -0.08
    POSITIVE LOGITS
    çŃIJ
    0.10
    âŃķ
    0.09
    建ç«ĭ
    0.09
    æĥ¯
    0.09
    çĺ¿
    0.08
    inine
    0.08
    á»İ
    0.08
    å°Ħ
    0.08
    åIJĥçļĦ
    0.08
    ickers
    0.08
    Activations Density 0.084%

    No Known Activations