© 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. 49627
    Prev
    Next
    INDEX
    Explanations

    equivalent dose, transistor, neutron, noise, beam

    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
    çĵľ
    -0.11
    æĨ¬
    -0.09
    æĮ¤
    -0.09
    çIJIJ
    -0.09
    orado
    -0.08
    åıijåĬ¨
    -0.08
    没æľīæĥ³åĪ°
    -0.08
    xoops
    -0.08
    çĽ¥
    -0.08
    åIJ¸
    -0.08
    POSITIVE LOGITS
    IDA
    0.10
     Ø¥ØŃ
    0.10
    ISO
    0.10
     trÆ°ng
    0.09
    æį¢
    0.09
    å¤Ħæĸ¹
    0.09
    æ¤įæłij
    0.09
    ÑĤаÑĢ
    0.09
    å¼Ħ
    0.09
    pak
    0.09
    Activations Density 0.124%

    No Known Activations