© 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. 51579
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
    嵩
    -0.09
    gest
    -0.08
    è¿Ļ家ä¼Ļ
    -0.08
     IPP
    -0.08
    lut
    -0.08
    Opp
    -0.08
    æīij
    -0.08
     pers
    -0.08
    CTION
    -0.08
    uet
    -0.07
    POSITIVE LOGITS
    樱æ¡ĥ
    0.10
    è¯Ħ论
    0.10
    éļ¾é¢ĺ
    0.09
    çłļ
    0.09
    忸
    0.09
    京津
    0.09
    åĩłçĤ¹
    0.09
    ç¡ķ
    0.08
    åħ·ä½ĵåĨħ容
    0.08
    Squared
    0.08
    Activations Density 0.199%

    No Known Activations