© 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. 18888
    Prev
    Next
    INDEX
    Explanations

    damage or destruction

    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
    举
    -0.10
    ยà¸ģ
    -0.10
     Ped
    -0.09
    御
    -0.09
    çŃ¹åĪĴ
    -0.09
    èĿ®
    -0.09
    饿
    -0.08
    å¾Ĺ天
    -0.08
    otta
    -0.08
    çģ«çĥŃ
    -0.08
    POSITIVE LOGITS
    æįŁåĿı
    0.18
    æ¯ģ
    0.16
    财产
    0.14
     damage
    0.14
    çł´åĿı
    0.14
    Damage
    0.13
     Damage
    0.13
    damage
    0.13
    æįŁ
    0.13
     destruction
    0.12
    Activations Density 0.102%

    No Known Activations