© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52074
    Prev
    Next
    INDEX
    Explanations

    terrorism and terrorist groups

    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
    åıĮçľ¼
    -0.10
    checker
    -0.09
    _trap
    -0.09
    als
    -0.09
    åIJ¬è§ģ
    -0.08
    yles
    -0.08
    aye
    -0.08
    åıij表
    -0.08
    tracer
    -0.08
    yard
    -0.08
    POSITIVE LOGITS
    çĻ½æ²Ļ
    0.09
    åĬłç´§
    0.09
    æĢĸ
    0.09
     incub
    0.09
    _SUPPORT
    0.08
    ÑĢÑĥпп
    0.08
     ETA
    0.08
     limbs
    0.08
    æĹ»
    0.08
     limp
    0.08
    Activations Density 0.099%

    No Known Activations