© 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. 37952
    Prev
    Next
    INDEX
    Explanations

    birds flying or flushed

    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
    祯
    -0.09
    Ñģел
    -0.09
    大èĩªçĦ¶
    -0.09
     ÑģовеÑĢÑĪен
    -0.08
    象
    -0.08
    å·¾
    -0.08
    éĩĩéĽĨ
    -0.08
    acha
    -0.08
    /widget
    -0.08
    alen
    -0.08
    POSITIVE LOGITS
    undy
    0.10
    æ´²
    0.09
    StateManager
    0.09
    åIJĮä¼´
    0.09
    åį·
    0.09
    æķ£
    0.08
    ç®ĹäºĨ
    0.08
    ystate
    0.08
    çĤ¹åĩ»æŁ¥çľĭ
    0.08
    ayed
    0.08
    Activations Density 0.038%

    No Known Activations