© 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. 55262
    Prev
    Next
    INDEX
    Explanations

    shooting or violence against people

    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
    éĻ·éĺ±
    -0.10
    æĶ¯æŁ±
    -0.09
    伪
    -0.09
     pitchers
    -0.09
     quake
    -0.09
    çĻ«çĹ«çĹħ
    -0.09
    èĽĬ
    -0.09
    æ·³
    -0.09
    æı
    -0.08
    æĹłå¿§
    -0.08
    POSITIVE LOGITS
    åŃIJå¼¹
    0.12
     shooting
    0.10
    å°Ħ
    0.10
     Shot
    0.10
    Shot
    0.10
    伤åı£
    0.10
     shot
    0.09
    shoot
    0.09
    hit
    0.09
    æŃ¢
    0.09
    Activations Density 0.063%

    No Known Activations