© 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. 10012
    Prev
    Next
    INDEX
    Explanations

    financial relief and loans

    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
    çİ°åĩº
    -0.09
    常年
    -0.09
    ä¸ķ
    -0.08
    宪
    -0.08
    legg
    -0.08
    çĵ¢
    -0.08
    åĪĨ管
    -0.08
    ä¾ĭè¡Į
    -0.08
     Claude
    -0.08
    è¿ĻäºĽéĹ®é¢ĺ
    -0.08
    POSITIVE LOGITS
    纾
    0.11
    åĪºæ¿Ģ
    0.10
     stimulus
    0.10
    é©°æı´
    0.10
    æĬļ
    0.10
     relief
    0.10
    æı´
    0.10
    åı²è¯Ĺ
    0.09
    çģ¾éļ¾
    0.09
    æķijåĬ©
    0.09
    Activations Density 0.076%

    No Known Activations