© 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. 38253
    Prev
    Next
    INDEX
    Explanations

    charity events, auctions, and rides

    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
    æѤ类
    -0.09
    èŁł
    -0.09
    oya
    -0.08
    natal
    -0.08
    ains
    -0.08
    ings
    -0.08
    èĩªæķij
    -0.08
    缴æݥ影åĵį
    -0.08
    æ¥ł
    -0.08
    çģ¾åĮº
    -0.08
    POSITIVE LOGITS
    èıĸ
    0.10
    Ùħد
    0.09
    bubble
    0.09
    è¯¾æľ¬
    0.09
    âĦĭ
    0.09
    å¢ŀè¿Ľ
    0.09
    åķĸ
    0.09
    subclass
    0.08
    åĪĿ次
    0.08
    relationships
    0.08
    Activations Density 0.025%

    No Known Activations