© 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. 38677
    Prev
    Next
    INDEX
    Explanations

    antigens

    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
    äºĨä¸Ģ份
    -0.09
    äºĨä¸Ģåı£
    -0.09
    èķŀ
    -0.08
    AuthToken
    -0.08
    ordinates
    -0.08
     Bord
    -0.08
    iative
    -0.08
     esc
    -0.08
    éļIJ身
    -0.08
    izu
    -0.08
    POSITIVE LOGITS
    íħIJ
    0.09
    itet
    0.09
     ---------------------------------------------------------------------------↵
    0.09
    好åĥıæĺ¯
    0.08
    åľ¨åħ¨åĽ½
    0.08
    uite
    0.08
    å¹Į
    0.08
    PARSE
    0.08
    çģ¯åħī
    0.08
    èĥĥèĤł
    0.08
    Activations Density 0.082%

    No Known Activations