© 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. 51286
    Prev
    Next
    INDEX
    Explanations

    not uncommon / common practice

    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
    åĭ¿
    -0.11
    loth
    -0.09
    _TESTS
    -0.08
    borough
    -0.08
    è°Ĵ
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    BOR
    -0.08
     sẵn
    -0.08
    æݼ
    -0.08
    .Must
    -0.08
    POSITIVE LOGITS
    æĶ¶åĪ°
    0.09
    ä¸Ģæľ¬ä¹¦
    0.09
    èĮ«çĦ¶
    0.09
    æĦŁåĪ°
    0.09
    åıªè§ģ
    0.08
    sr
    0.08
    åij¨æľŁ
    0.08
    éĶŃ
    0.08
    umo
    0.08
    åĥ°
    0.08
    Activations Density 0.027%

    No Known Activations