© 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. 35959
    Prev
    Next
    INDEX
    Explanations

    collective entities and groups

    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
    еÑĨ
    -0.10
    ãģ¿ãģŁãģĦ
    -0.10
    hell
    -0.09
    .tail
    -0.09
    è¯ĺ
    -0.08
    ROWS
    -0.08
    å´¤
    -0.08
    _DS
    -0.08
    éĺµ
    -0.08
    æĽ
    -0.08
    POSITIVE LOGITS
    äºĭä¸ļ
    0.13
    大å±Ģ
    0.11
    è¿Ļ个èģĮä¸ļ
    0.11
    åħļåĴĮåĽ½å®¶
    0.10
     society
    0.10
    åĪ©çĽĬ
    0.09
    éĿ¢åīį
    0.09
    å¯Ħ
    0.09
    hest
    0.09
    äºĭæ¥Ń
    0.09
    Activations Density 0.056%

    No Known Activations