© 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. 36367
    Prev
    Next
    INDEX
    Explanations

    wood and its surroundings

    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
     buc
    -0.10
    ãģĮãĤī
    -0.08
    导读
    -0.08
    naire
    -0.08
    åħ¶æīĢ
    -0.08
    èħ±
    -0.08
    bsp
    -0.08
    裾
    -0.08
    ivan
    -0.08
    çľ¼éĥ¨
    -0.08
    POSITIVE LOGITS
    lands
    0.10
    stock
    0.09
    æŁĪ
    0.09
    locker
    0.09
    å±ij
    0.09
    樨
    0.09
    ings
    0.09
     админиÑģÑĤÑĢа
    0.09
     lou
    0.08
    HAM
    0.08
    Activations Density 0.026%

    No Known Activations