© 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. 21266
    Prev
    Next
    INDEX
    Explanations

    burning tyres, burning Israeli flag, burning a Koran, set trash bins on fire

    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
    è´
    -0.09
    ä¸ĢåIJ¬
    -0.08
    åIJĿ
    -0.08
    chef
    -0.08
    _SU
    -0.08
    ieri
    -0.08
     Sahara
    -0.08
    æĭĽå¾ħ
    -0.08
    åıĸ代
    -0.08
    åݲ
    -0.08
    POSITIVE LOGITS
    æŀģ端
    0.11
    æij§æ¯ģ
    0.10
    æĮł
    0.10
    çĦļçĥ§
    0.10
    磼
    0.10
    çĥŁèĬ±
    0.10
    yne
    0.10
    æİĢ
    0.09
    çĩĥ
    0.09
    æĬµåĪ¶
    0.09
    Activations Density 0.062%

    No Known Activations