© 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. 36906
    Prev
    Next
    INDEX
    Explanations

    states of being

    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
    æĮĩçĤ¹
    -0.09
    èĢĮéĿŀ
    -0.09
     Miche
    -0.09
    å·²ä¹ħ
    -0.08
    çĶµç¼Ĩ
    -0.08
    çļĦæĦŁè§ī
    -0.08
    å¡Į
    -0.08
    åĿį
    -0.08
    饺åŃIJ
    -0.08
    ¤í
    -0.08
    POSITIVE LOGITS
    fi
    0.08
    iable
    0.08
    ntl
    0.08
    æĬĬèĩªå·±çļĦ
    0.08
    BUR
    0.08
     Ñģобой
    0.08
     mold
    0.08
    posted
    0.08
    æĬĬ
    0.08
    ysz
    0.08
    Activations Density 0.150%

    No Known Activations