© 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. 49124
    Prev
    Next
    INDEX
    Explanations

    marine life and scientific 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
    owy
    -0.09
    ellan
    -0.09
    IGIN
    -0.09
    åľŃ
    -0.09
    ãģĤãĤĬ
    -0.08
    éĶ¯
    -0.08
    dap
    -0.08
    財
    -0.08
    çĶŁäº§èĥ½åĬĽ
    -0.08
    emodel
    -0.08
    POSITIVE LOGITS
    æ®ĭéħ·
    0.10
    æ´Ħ
    0.10
    好ä¸į容æĺĵ
    0.10
    çģ
    0.09
    è£ķ
    0.09
    çIJĨäºĭéķ¿
    0.09
    çĶŁæ´»çݯå¢ĥ
    0.09
    æĴŃæĬ¥
    0.09
    simp
    0.09
    大æĪ·
    0.09
    Activations Density 0.103%

    No Known Activations