© 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. 53053
    Prev
    Next
    INDEX
    Explanations

    Magento namespace or Macedonian

    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
    æ¿Ĥ
    -0.09
    åĩºæ¸¸
    -0.09
    éĻ¢åŃIJéĩĮ
    -0.09
    客家
    -0.08
    磾
    -0.08
    Extras
    -0.08
    à®±
    -0.08
     evolutionary
    -0.08
    ULAR
    -0.08
    å°¤
    -0.08
    POSITIVE LOGITS
    ç´«
    0.10
    çĮľ
    0.10
    读åIJİ
    0.09
    龸
    0.09
    ATAR
    0.09
    èħ»
    0.09
    ål
    0.09
    ospel
    0.09
    .dispatch
    0.09
    ijľ
    0.09
    Activations Density 0.148%

    No Known Activations