© 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. 8851
    Prev
    Next
    INDEX
    Explanations

    criminal charges and prison sentences

    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
    轻微
    -0.10
     Arrest
    -0.10
    aber
    -0.09
    cur
    -0.09
    lice
    -0.09
    æ»ŀ
    -0.09
    çĬ¯ç½ª
    -0.09
    æ²»å®ī
    -0.09
    æĭĺçķĻ
    -0.09
    失è°ĥ
    -0.09
    POSITIVE LOGITS
    ç»ĪçĶŁ
    0.10
    æĭ¼åij½
    0.10
    åŁºåĩĨ
    0.09
    æ°¸éģł
    0.09
    æ°¸è¿ľ
    0.09
    éĹ®çŃĶ
    0.09
     Purple
    0.08
    建çŃijå¸Ī
    0.08
    è¾ŀ
    0.08
    geh
    0.08
    Activations Density 0.072%

    No Known Activations