© 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. 8187
    Prev
    Next
    INDEX
    Explanations

    specifications and details

    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
    ÑĢоÑģÑģ
    -0.10
     ва
    -0.09
    å·ħ
    -0.09
    eton
    -0.09
    æľī害
    -0.08
     Shade
    -0.08
    å®ļå¾ĭ
    -0.08
    éłĨ
    -0.08
    çķħéĶĢ
    -0.08
     ifdef
    -0.08
    POSITIVE LOGITS
     parameters
    0.12
     details
    0.11
    è§Ħæł¼
    0.10
    parameters
    0.10
     particulars
    0.10
     dimensions
    0.09
    åIJĦæĸ¹éĿ¢
    0.09
    详æĥħ
    0.09
     specifications
    0.09
    å¦Ĥä¸ĭ
    0.09
    Activations Density 0.153%

    No Known Activations