© 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. 52515
    Prev
    Next
    INDEX
    Explanations

    cant followed by resolve

    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
    åŃIJéĩĮ
    -0.11
    åį°åıij
    -0.09
    geist
    -0.09
    ìķ¼
    -0.09
    sume
    -0.09
    omo
    -0.09
    Å¡t
    -0.08
    æĹłéľĢ
    -0.08
    çĻ½äºij
    -0.08
    åŀļ
    -0.08
    POSITIVE LOGITS
    ç»ĦæĪIJéĥ¨åĪĨ
    0.10
    åĽŀé¦ĸ
    0.10
    åģļåĪ°
    0.10
    åħ¨éĿ¢åıijå±ķ
    0.09
    achu
    0.09
    PUR
    0.09
     اÙĦØŃÙĬ
    0.09
    欣èµı
    0.09
    åĽŀäºĭ
    0.09
    wel
    0.09
    Activations Density 0.006%

    No Known Activations