© 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. 9276
    Prev
    Next
    INDEX
    Explanations

    farm and ranch

    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
    å··
    -0.11
    çıĬçijļ
    -0.11
    大è¡Ĺ
    -0.10
    è¿Ļ座åŁİå¸Ĥ
    -0.10
    èĹ»
    -0.09
    çļĦåŁİå¸Ĥ
    -0.09
    åĩºéŨ
    -0.09
    éĺŁä¼į
    -0.09
     alley
    -0.09
     city
    -0.09
    POSITIVE LOGITS
    åĨľåľº
    0.17
    åºĦåĽŃ
    0.14
     farm
    0.14
    çĶŁäº§åŁºåľ°
    0.13
    çĶ°åĽŃ
    0.12
    å±±åºĦ
    0.12
    åŁºåľ°
    0.11
    farm
    0.11
     ranch
    0.11
    çī§åľº
    0.11
    Activations Density 0.178%

    No Known Activations