© 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. 21013
    Prev
    Next
    INDEX
    Explanations

    settle in or be alone

    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
    åIJĮè¡Į
    -0.10
    åIJį声
    -0.09
    å¯Ħ
    -0.09
    åĽŀåİ»
    -0.09
    çī§
    -0.09
    æºIJæºIJä¸įæĸŃ
    -0.09
     vending
    -0.08
    åĶ¢
    -0.08
     RET
    -0.08
    äºĶåįĥ
    -0.08
    POSITIVE LOGITS
    客åİħ
    0.13
     household
    0.12
    家åĬ¡
    0.11
    室åĨħ
    0.10
    åģļé¥Ń
    0.10
    çľĭçĶµè§Ĩ
    0.10
    å±ħ室
    0.10
    åľ¨å®¶
    0.10
    å±ħ家
    0.10
    家å±ħ
    0.10
    Activations Density 0.091%

    No Known Activations