© 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. 53729
    Prev
    Next
    INDEX
    Explanations

    energy companies

    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
    ears
    -0.09
    ullo
    -0.09
    主ç¼ĸ
    -0.08
    à¹ģà¸Ļ
    -0.08
    ollo
    -0.08
    worth
    -0.08
    缴è§Ĥ
    -0.08
    kov
    -0.08
    令
    -0.08
    è´Ŀå°Ķ
    -0.08
    POSITIVE LOGITS
    çĶµæ°Ķ
    0.10
    è¯Ŀ说
    0.10
    çĶµåĬĽ
    0.10
    çĩĥçħ¤
    0.09
    åĹŁ
    0.09
    åıijçĶµ
    0.09
    åħ¬åı¸çļĦ
    0.09
    责任æĦŁ
    0.09
    ç¿ģ
    0.09
    çĶµçº¿
    0.09
    Activations Density 0.033%

    No Known Activations