© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21046
    Prev
    Next
    INDEX
    Explanations

    win or defeat results

    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
    èĪģ
    -0.10
    pus
    -0.09
    SHOT
    -0.09
    çĭĴ
    -0.09
    POSE
    -0.09
     اÙĦÙĤض
    -0.08
    æ¢Ĩ
    -0.08
    太ä¹ħ
    -0.08
    éĹ©
    -0.08
    çĮ´
    -0.08
    POSITIVE LOGITS
    /disc
    0.10
    perms
    0.09
    @student
    0.09
    身亡
    0.09
    åħ¨è¿ĩç¨ĭ
    0.09
    äºĨèĩªå·±çļĦ
    0.08
    çķĻåѦçĶŁ
    0.08
    æĬµåĪ¶
    0.08
    /exp
    0.08
    çİĩè¾¾
    0.08
    Activations Density 0.015%

    No Known Activations