© 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. 49021
    Prev
    Next
    INDEX
    Explanations

    gun related terms

    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
    çĻ¾
    -0.10
    çī§
    -0.10
    çķħéĢļ
    -0.09
    UP
    -0.08
    DVD
    -0.08
    æİī
    -0.08
    åĨ³æĪĺ
    -0.08
     Rosenberg
    -0.07
    ran
    -0.07
     kne
    -0.07
    POSITIVE LOGITS
    esses
    0.10
    åıĸè¯ģ
    0.10
    æīĭèĩĤ
    0.10
     stead
    0.10
    acement
    0.10
    æĮĩçĤ¹
    0.10
    å¾Ī好çļĦ
    0.10
    çĽ¸æľº
    0.10
    æľĽ
    0.09
    æı¡
    0.09
    Activations Density 0.113%

    No Known Activations