© 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. 18661
    Prev
    Next
    INDEX
    Explanations

    egg shell quality

    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
    Lik
    -0.11
     lik
    -0.10
    Sibling
    -0.08
     назнаÑĩен
    -0.08
     Lik
    -0.08
    æĿĥå¨ģ
    -0.08
    åıij声
    -0.08
    9
    -0.08
    0
    -0.08
     thumbs
    -0.08
    POSITIVE LOGITS
    溯æºIJ
    0.10
    éĹ´éļĶ
    0.10
    åĨħå¤ĸ
    0.10
    éĺ²çĽĹ
    0.09
    æľīä¿¡å¿ĥ
    0.09
    åŀ©
    0.09
    _supply
    0.09
    meg
    0.09
    é¦Ļåij³
    0.09
    åħ¨èĩªåĬ¨
    0.09
    Activations Density 0.104%

    No Known Activations