© 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. 56581
    Prev
    Next
    INDEX
    Explanations

    past tense of 'to be' + age or past experience

    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
    eling
    -0.10
    pez
    -0.09
    ä»İèĢĮ使
    -0.09
    kos
    -0.09
    ä»ĸä»¬åľ¨
    -0.09
    åıªè¦ģä½ł
    -0.09
    .sb
    -0.09
    ä¼ļéķ¿
    -0.08
    çĶ¨è½¦
    -0.08
     greatly
    -0.08
    POSITIVE LOGITS
    度è¿ĩ
    0.10
    ellite
    0.09
    aviest
    0.08
    å¼ĢæĪ·
    0.08
    proper
    0.08
    å´ĩé«ĺ
    0.08
    æľīæĿ¡ä»¶
    0.08
    æīįå¹²
    0.08
     boss
    0.08
    æľīæĦıä¹ī
    0.08
    Activations Density 0.057%

    No Known Activations