© 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. 53359
    Prev
    Next
    INDEX
    Explanations

    affordability

    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
    æľīæĦı
    -0.09
    engl
    -0.09
    æľªæĪIJ
    -0.09
    æĢ»çļĦ
    -0.09
    readonly
    -0.08
    çĶ³æĬ¥
    -0.08
    宵
    -0.08
    UPS
    -0.08
    rys
    -0.08
    å¾Ħ
    -0.08
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.19
     afford
    0.14
     affordability
    0.13
    è´Łæĭħ
    0.12
     affordable
    0.11
    aff
    0.11
    æĺĤè´µ
    0.10
    没éĴ±
    0.10
    ordable
    0.10
    佯
    0.10
    Activations Density 0.041%

    No Known Activations