© 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. 48164
    Prev
    Next
    INDEX
    Explanations

    querying for rows

    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
    åħīæ»ij
    -0.11
    GORITHM
    -0.09
    èįĶæŀĿ
    -0.09
    çijĹ
    -0.09
    åľ¨ä¸ĢæĹģ
    -0.09
    callbacks
    -0.09
    /LICENSE
    -0.09
    åķIJ
    -0.09
    æİ¥åıĹ
    -0.09
    ][_
    -0.09
    POSITIVE LOGITS
    æ·±å±Ĥ
    0.10
    ordin
    0.09
     joins
    0.09
    综åIJĪæĢ§
    0.09
    è¿ĩ滤
    0.09
     query
    0.08
    éģį
    0.08
    æ·±å±Ĥ次
    0.08
    erg
    0.08
    读
    0.08
    Activations Density 0.674%

    No Known Activations