© 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. 3640
    Prev
    Next
    INDEX
    Explanations

    nature and its adjacent words

    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
    庶
    -0.10
    æĥ«
    -0.09
    æĭį
    -0.09
    ÙĬØ´
    -0.09
    èĩªè¡Į车
    -0.09
    èĤ
    -0.08
     Reyes
    -0.08
    stantiate
    -0.08
    AGE
    -0.08
    åĤĴ
    -0.08
    POSITIVE LOGITS
     اÙĦØ®ÙĦ
    0.11
    alez
    0.10
    åħµ
    0.10
     naturally
    0.09
    aleza
    0.09
    èĩªçĦ¶
    0.09
     nature
    0.09
    aturally
    0.09
    çķĮçļĦ
    0.09
    asha
    0.09
    Activations Density 0.034%

    No Known Activations