© 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. 8240
    Prev
    Next
    INDEX
    Explanations

    government regulations and organizations

    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
    è¿·
    -0.10
     Grat
    -0.10
    å½ĵåľ°äºº
    -0.09
     peg
    -0.09
    ä¾µ
    -0.08
    burg
    -0.08
    éĻį临
    -0.08
    utz
    -0.08
     Peg
    -0.08
    èij
    -0.08
    POSITIVE LOGITS
    prog
    0.09
    éĥ¦
    0.08
     Shank
    0.08
    ä¼ĹçŃ¹
    0.08
    ÃŃcio
    0.08
    OMB
    0.08
    PMC
    0.08
    ä¸ĢéĤĬ
    0.08
    æľĽåİ»
    0.08
    è¿ľæ´ĭ
    0.08
    Activations Density 0.081%

    No Known Activations