© 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. 19118
    Prev
    Next
    INDEX
    Explanations

    tongue

    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
    åıįå¼¹
    -0.10
    èħ°
    -0.09
    strand
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    çĺ¾
    -0.09
    ç¡Į
    -0.09
    åıĪ好
    -0.09
    海滨
    -0.09
    纰
    -0.09
    æĩ¿
    -0.08
    POSITIVE LOGITS
    èĪĮ头
    0.13
    èĪĮ
    0.11
     tongues
    0.11
     tongue
    0.10
    èĪĮå°ĸ
    0.09
     tip
    0.09
    çģµæ´»
    0.09
    iniz
    0.09
    éĺľ
    0.08
    æłĩåĩĨåĮĸ
    0.08
    Activations Density 0.045%

    No Known Activations