© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21515
    Prev
    Next
    INDEX
    Explanations

    mitochondrial, chloroplasts, organelle genomes

    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
    åıijå¸ĥåħ¬åijĬ
    -0.10
    éĽ¾
    -0.09
    agraph
    -0.09
    azen
    -0.08
    æ¯ı个人çļĦ
    -0.08
     runners
    -0.08
    ä»»
    -0.08
    æĻºæħ§åŁİå¸Ĥ
    -0.08
    åĨ»
    -0.08
    nil
    -0.08
    POSITIVE LOGITS
    GCC
    0.09
    uant
    0.09
    encies
    0.09
    çľĭ书
    0.09
    çĥĽ
    0.09
    磸
    0.09
    çĤī
    0.09
    æ¯ĭ
    0.08
    嵩
    0.08
    ä¸įéĶĻ
    0.08
    Activations Density 0.321%

    No Known Activations