© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52437
    Prev
    Next
    INDEX
    Explanations

    approach to a method

    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
    çŀ¬éĹ´
    -0.08
    åıĺæį¢
    -0.08
     enjo
    -0.08
    æķ¦
    -0.08
    æľīæľŁ
    -0.08
    ä¸Ģçŀ¬éĹ´
    -0.08
     McCorm
    -0.08
    dale
    -0.08
    ×ł×¡
    -0.08
    .ylabel
    -0.07
    POSITIVE LOGITS
     approach
    0.38
     Approach
    0.34
    appro
    0.29
    Appro
    0.27
     approached
    0.25
     approaches
    0.25
    _appro
    0.25
     подÑħод
    0.20
     approaching
    0.20
     APPRO
    0.19
    Activations Density 0.173%

    No Known Activations