© 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. 31412
    Prev
    Next
    INDEX
    Explanations

    pollution types and consequences

    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
    à¹Ĥà¸Ĺษ
    -0.10
    åĦ¿
    -0.10
    æĢ§åij½
    -0.09
    reo
    -0.09
    èģĥ
    -0.09
    çĸ¯çĭĤ
    -0.09
    åŃIJéĩĮ
    -0.09
    OfWeek
    -0.09
    æĢ
    -0.09
    <Void
    -0.09
    POSITIVE LOGITS
    rieb
    0.09
    ر
    0.09
    brush
    0.09
    æºIJ
    0.08
    æ®Ĩ
    0.08
    jin
    0.08
    urge
    0.08
    erview
    0.08
    uru
    0.08
    gram
    0.08
    Activations Density 0.010%

    No Known Activations