© 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. 35632
    Prev
    Next
    INDEX
    Explanations

    adjective endings -ly, -ed, -ing

    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
    æ·ħ
    -0.12
    rez
    -0.10
    defs
    -0.10
    èļ¤
    -0.10
    ede
    -0.10
    iez
    -0.10
    æľ¦
    -0.09
    å¼ĢéŨ
    -0.09
    Óĵ
    -0.09
    .buf
    -0.09
    POSITIVE LOGITS
    -haired
    0.08
    eyed
    0.08
    olly
    0.08
    uras
    0.08
    åĨħåľ¨
    0.08
    ÙĨب
    0.08
    饿
    0.08
    ãģĬãģı
    0.07
    uis
    0.07
    ä¸įå¿ĺ
    0.07
    Activations Density 0.035%

    No Known Activations