© 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. 8767
    Prev
    Next
    INDEX
    Explanations

    anticipate

    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
    loth
    -0.09
    ä½Ĩè¿Ļ
    -0.09
    ngo
    -0.09
    ath
    -0.09
    åįĥå¹´
    -0.08
    ä½Ĩæĺ¯æĪij
    -0.08
    çĽ¸å¯¹æĿ¥è¯´
    -0.08
    cke
    -0.08
    积æŀģæݢ索
    -0.08
    豸
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħ
    0.11
    ahead
    0.10
     ahead
    0.10
    è¦ģåģļ好
    0.09
    æľªæĿ¥
    0.09
    anse
    0.09
    igne
    0.09
     اÙĦÙħستÙĤبÙĦ
    0.09
     Lau
    0.09
     future
    0.08
    Activations Density 0.015%

    No Known Activations