© 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. 58530
    Prev
    Next
    INDEX
    Explanations

    right to

    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
    åıĺåİĭ
    -0.08
    ä½Ī
    -0.08
    è¿Ļç§įæĥħåĨµ
    -0.08
    aday
    -0.08
    æ¾į
    -0.08
    ä¸ĭæ»ij
    -0.08
     rode
    -0.08
    Ñģка
    -0.08
     scandal
    -0.08
    um
    -0.08
    POSITIVE LOGITS
    ä»Ĺ
    0.10
    æı¡
    0.10
     Chandler
    0.09
    çĻ»
    0.09
    鸡
    0.09
    Terms
    0.09
    USES
    0.09
    ãĥģãĤ§
    0.09
    ä¸įçĶ±
    0.09
    /terms
    0.09
    Activations Density 0.012%

    No Known Activations