© 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. 21194
    Prev
    Next
    INDEX
    Explanations

    planets and celestial bodies

    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
    alysis
    -0.11
    çĥ¬
    -0.09
    esda
    -0.09
    ibi
    -0.09
    spot
    -0.08
    imity
    -0.08
    arya
    -0.08
    ุ
    -0.08
    holm
    -0.08
    ocking
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.12
    ally
    0.11
    draft
    0.10
    tte
    0.10
    æĮ¯åħ´
    0.10
    ä»Ģä¹ĪåİŁåĽł
    0.09
    ETS
    0.09
    æĥħ人
    0.09
    侪
    0.09
    åĮºåĪ«
    0.09
    Activations Density 0.008%

    No Known Activations