© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23021
    Prev
    Next
    INDEX
    Explanations

    land and outdoor spaces

    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
     alley
    -0.12
    alley
    -0.11
    .experimental
    -0.11
    å··
    -0.10
    âĦķ
    -0.10
    æĹ¶ä»£çļĦ
    -0.10
    路人
    -0.10
    éĺµåľ°
    -0.09
    fal
    -0.09
    åĬ©éķ¿
    -0.09
    POSITIVE LOGITS
    grounds
    0.09
    ishi
    0.09
    èĶĵ
    0.09
    嵬
    0.08
    ä¸ĬçļĦ
    0.08
    麽
    0.08
    tog
    0.08
    为ä¹ĭ
    0.08
    ä¹ĥèĩ³
    0.08
    embr
    0.08
    Activations Density 0.027%

    No Known Activations