© 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. 61535
    Prev
    Next
    INDEX
    Explanations

    school shootings and shooters

    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
    èĨı
    -0.12
    åħ¬è¯ģ
    -0.10
    çĽijå¯Ł
    -0.10
    è°ı
    -0.09
    orial
    -0.09
    CRYPT
    -0.09
    媳å¦ĩ
    -0.08
    æ²¥
    -0.08
     gw
    -0.08
    çĶµç½ij
    -0.08
    POSITIVE LOGITS
    æĪ¾
    0.10
    rup
    0.09
    ç½
    0.09
    æ¯Ķçī¹
    0.09
     Bott
    0.09
    éľĩæħij
    0.09
    rô
    0.09
    parent
    0.08
    æī©
    0.08
    çĵ¶åŃIJ
    0.08
    Activations Density 0.068%

    No Known Activations