© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40014
    Prev
    Next
    INDEX
    Explanations

    wanted fugitives, reward, bounty, warrant, hunted

    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
    èݳ
    -0.10
    åģļè¿ĩ
    -0.10
    é¦Ĵ头
    -0.10
    äu
    -0.10
    é¢Ħè§ģ
    -0.10
    æķŀå¼Ģ
    -0.09
    èĥĥåı£
    -0.09
    ç¿»å¼Ģ
    -0.09
    eteor
    -0.09
    驳
    -0.09
    POSITIVE LOGITS
     fug
    0.12
    éĢĥ
    0.11
    éĢĭ
    0.11
    éĢĥè·ij
    0.11
    éĢĥèĦ±
    0.10
    éĢĥéģ¿
    0.09
     escaped
    0.09
    追æ±Ĥ
    0.09
    æĬĵæįķ
    0.09
    æĬ¼
    0.09
    Activations Density 0.103%

    No Known Activations