© 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. 47876
    Prev
    Next
    INDEX
    Explanations

    soldering, joining, fusion

    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
    çŃĽ
    -0.10
    Ìģ
    -0.10
    æĦıåĽ¾
    -0.09
    (SK
    -0.09
    ign
    -0.08
    å¹½
    -0.08
    gest
    -0.08
    vae
    -0.08
    oley
    -0.07
    é©
    -0.07
    POSITIVE LOGITS
    峡
    0.10
     solder
    0.10
    çĦĬ
    0.09
    顶å±Ĥ
    0.09
     Ivy
    0.09
    俱
    0.09
     bri
    0.09
    bor
    0.09
    åĨĴ
    0.09
    éĢłèĪ¹
    0.09
    Activations Density 0.066%

    No Known Activations