© 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. 53875
    Prev
    Next
    INDEX
    Explanations

    homicide and crime cases

    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
     Offensive
    -0.09
     abst
    -0.09
    _damage
    -0.09
    èħĨ
    -0.09
    è¯Ħå§Ķ
    -0.09
     offensive
    -0.08
    æĸĹ
    -0.08
    sst
    -0.08
    åīįè¾Ī
    -0.08
    สมา
    -0.08
    POSITIVE LOGITS
    æĿĢ人
    0.10
    æĿĢæŃ»
    0.10
     spouses
    0.10
    æĿĢäºĨ
    0.09
    æŃ»äº¡
    0.09
    house
    0.09
    殺
    0.09
    isman
    0.09
     homicide
    0.09
    æĦıåĽ¾
    0.09
    Activations Density 0.109%

    No Known Activations