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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35597
    Prev
    Next
    INDEX
    Explanations

    hormone preparations

    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
    STALL
    -0.09
    å½ĵåľ°äºº
    -0.09
    åIJĥåĪ°
    -0.09
     Shia
    -0.08
    åħ¶æīĢ
    -0.08
    人æµģ
    -0.08
    åľºåĿĩ
    -0.08
     bol
    -0.08
    ä¸īä½įä¸Ģä½ĵ
    -0.08
    æ½ľ
    -0.08
    POSITIVE LOGITS
    bers
    0.10
    unist
    0.09
    phon
    0.09
     Uri
    0.08
    çķ¹
    0.08
    ëģ¼
    0.08
     Ole
    0.08
    ï¸
    0.08
    åĩŃçĿĢ
    0.08
     restitution
    0.08
    Activations Density 0.009%

    No Known Activations