© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38308
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
    actively
    -0.10
    edBy
    -0.10
    æĦĶ
    -0.09
    identally
    -0.09
    ç½²
    -0.09
    atively
    -0.09
    æģĴ
    -0.09
    istically
    -0.09
    ishly
    -0.08
    ught
    -0.08
    POSITIVE LOGITS
    lays
    0.12
    èıŁ
    0.10
     Boeh
    0.09
    semb
    0.09
    å³¥
    0.09
    boarding
    0.09
    åĨ¢
    0.09
    éľĵ
    0.09
    çĶ°åĽŃ
    0.09
    ç»®
    0.08
    Activations Density 1.209%

    No Known Activations