© 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. 32055
    Prev
    Next
    INDEX
    Explanations

    state-of-the-art equipment

    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
    头åıij
    -0.09
    æĪIJåĬŁä¸¾åĬŀ
    -0.09
    åħ³éĹŃ
    -0.09
    è¿«åĪĩ
    -0.08
    bl
    -0.08
    å°§
    -0.08
    å¾Ģäºĭ
    -0.08
    .SDK
    -0.08
    rates
    -0.08
    trx
    -0.08
    POSITIVE LOGITS
     equipment
    0.10
     facilities
    0.10
    æľĢåħĪè¿ĽçļĦ
    0.10
    åħĪè¿ĽçļĦ
    0.09
    设æĸ½
    0.09
    çݰ代åĮĸ
    0.09
    çİ©æĦı
    0.09
    è£ħå¤ĩ
    0.09
    åħĪè¿ĽæĬĢæľ¯
    0.09
    è¨ŃåĤĻ
    0.09
    Activations Density 0.036%

    No Known Activations