© 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. 58878
    Prev
    Next
    INDEX
    Explanations

    others and people

    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
    æī¯
    -0.09
    oron
    -0.08
    çķĻä½ı
    -0.08
    èİħ
    -0.08
    =~
    -0.08
    ichi
    -0.08
    éĵ¿
    -0.08
    inic
    -0.08
    对人ä½ĵ
    -0.08
    æµĵæµĵçļĦ
    -0.08
    POSITIVE LOGITS
    åħ¶ä»ĸ人
    0.27
    ä»ĸ人
    0.23
    åĪ«äºº
    0.22
    åĪ«äººçļĦ
    0.20
     others
    0.20
    others
    0.17
    åĪ¥äºº
    0.17
     Others
    0.17
    åħ¶ä»ĸçݩ家
    0.16
    Others
    0.16
    Activations Density 0.246%

    No Known Activations