© 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. 26842
    Prev
    Next
    INDEX
    Explanations

    adhesive bonding

    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
    Ĥæķ°
    -0.09
    åħ¼èģĮ
    -0.09
    åºĩ
    -0.09
    éĺĤ
    -0.08
    æĪijçļĦå¿ĥ
    -0.08
    æĹ©çĤ¹
    -0.08
    èģĶç³»çĶµè¯Ŀ
    -0.08
     IGN
    -0.08
    ONS
    -0.08
    jin
    -0.08
    POSITIVE LOGITS
    éĻĦ
    0.10
     adhesive
    0.10
    lsi
    0.10
    ooks
    0.10
     attach
    0.09
    å¿Ļ
    0.09
    æĬĵ
    0.09
    æ¦ľ
    0.09
    Insn
    0.09
    å¸ĸ
    0.09
    Activations Density 0.122%

    No Known Activations