© 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. 36598
    Prev
    Next
    INDEX
    Explanations

    student loans and college expenses

    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
    å¢Ł
    -0.09
    ache
    -0.09
    reat
    -0.09
    ä½Ł
    -0.09
    驾é©Ń
    -0.09
    å¼±çĤ¹
    -0.08
    åIJĥè¿ĩ
    -0.08
     COPYRIGHT
    -0.08
    对æĪij们
    -0.08
    psilon
    -0.08
    POSITIVE LOGITS
     Protest
    0.09
    书éĻ¢
    0.09
    æĶ¶è´¹æłĩåĩĨ
    0.09
    åħ¨é¢Ŀ
    0.09
     Sharp
    0.09
    usat
    0.08
    åŃ¦è´¹
    0.08
     fees
    0.08
    AMI
    0.08
    æĶ¶è²»
    0.08
    Activations Density 0.016%

    No Known Activations