© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49502
    Prev
    Next
    INDEX
    Explanations

    playgrounds and structures

    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
    缸è§ģ
    -0.11
    ä»Ĺ
    -0.09
    çĤ¬
    -0.09
    fare
    -0.09
    粮油
    -0.09
     frag
    -0.09
    èıĬèĬ±
    -0.09
     gạo
    -0.09
    strand
    -0.08
    aisy
    -0.08
    POSITIVE LOGITS
    设æĸ½
    0.09
    çķĻ
    0.09
    设æĸ½å»ºè®¾
    0.09
    æľ¨è´¨
    0.09
    蹦
    0.09
    çķĻè¨ĢæĿ¿
    0.09
    åħ¥åı£
    0.09
     benches
    0.09
    æķĪ
    0.09
    ç»ĵæŀĦ
    0.08
    Activations Density 0.108%

    No Known Activations