© 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. 8222
    Prev
    Next
    INDEX
    Explanations

    media company names

    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
    éļıæŶéļı
    -0.12
    屯
    -0.09
    soon
    -0.09
    ваÑĤ
    -0.09
    arde
    -0.09
    /copyleft
    -0.09
    ÑĤÑı
    -0.09
    人æīį
    -0.09
    æ°´çĶµ
    -0.08
     Neg
    -0.08
    POSITIVE LOGITS
    çIJĨ
    0.09
    ics
    0.09
    èĥ¯
    0.09
    èĩªè§ī
    0.08
    vertiser
    0.08
    éĺĢ
    0.08
    nic
    0.08
    arch
    0.08
    èĦijåŃIJ
    0.08
    atica
    0.08
    Activations Density 0.015%

    No Known Activations