© 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. 37113
    Prev
    Next
    INDEX
    Explanations

    making choices

    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
    usher
    -0.09
     McA
    -0.09
    ðŁįħ
    -0.08
    èļģ
    -0.08
    æľªç»ı
    -0.08
    åĬ©
    -0.08
    æī£éĻ¤
    -0.08
    å¤ĩ
    -0.08
    å¦Ĩ
    -0.08
    DED
    -0.08
    POSITIVE LOGITS
    åĵªä¸Ģ个
    0.10
    éģ½
    0.10
     favorites
    0.10
    favorites
    0.10
    éļħ
    0.09
    èĪ«
    0.09
     favorite
    0.09
    çĪ±ç¾İ
    0.09
    è¿Ļä¹Īå¤ļ
    0.09
    riad
    0.09
    Activations Density 0.034%

    No Known Activations