© 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. 51107
    Prev
    Next
    INDEX
    Explanations

    production, use, threat, fire, demand

    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
    ustr
    -0.10
    èIJ½åĪ°
    -0.10
    æijĨåľ¨
    -0.09
    omer
    -0.09
    éĿ¢åīį
    -0.08
    oenix
    -0.08
    建åĨĽ
    -0.08
    fest
    -0.08
    amic
    -0.08
    uper
    -0.08
    POSITIVE LOGITS
    cá
    0.09
    è·¯ä¸Ĭ
    0.09
    大åħ¨
    0.08
    ä¸įæĸŃåĪĽæĸ°
    0.08
    é«ĺçŃīåŃ¦æł¡
    0.08
    åĪĨéĴŁå·¦åı³
    0.08
    æŁĦ
    0.08
    绿èī²çݯä¿Ŀ
    0.08
    åħ´ä¸ļ
    0.08
     Hubb
    0.08
    Activations Density 0.100%

    No Known Activations