© 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. 58781
    Prev
    Next
    INDEX
    Explanations

    stock market

    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
    rand
    -0.10
    ãģĦãģĭ
    -0.09
     bleed
    -0.09
    ä»ĺ
    -0.09
    icont
    -0.09
    سÙĥ
    -0.09
    è£Ķ
    -0.09
    èµĽåIJİ
    -0.09
    iendo
    -0.09
    身å¿ĥ
    -0.09
    POSITIVE LOGITS
    çµ²
    0.09
    holders
    0.09
    жи
    0.09
    ä¸Ŀ
    0.08
    ž
    0.08
     Bones
    0.08
    çĮĽçĥĪ
    0.08
    vely
    0.08
    çķ¹
    0.08
    纪念
    0.08
    Activations Density 0.031%

    No Known Activations