© 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. 2812
    Prev
    Next
    INDEX
    Explanations

    flame retardants and animal testing requirements

    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
    çĸĻ
    -0.12
    åįļ
    -0.10
     gang
    -0.09
    æ²³éģĵ
    -0.09
    çī§
    -0.08
     наÑģ
    -0.08
    ument
    -0.08
    åĭ¾
    -0.08
     racket
    -0.08
    ENG
    -0.08
    POSITIVE LOGITS
    æµĭè¯ķ
    0.11
     завод
    0.10
    alternate
    0.10
    沧
    0.10
    à¸Ĺà¸Ķสà¸Ńà¸ļ
    0.09
    沦
    0.09
    å·¥åİĤ
    0.09
    çĸ²æĥ«
    0.09
    éĺ²çģ«
    0.09
    tester
    0.09
    Activations Density 0.200%

    No Known Activations