© 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. 2936
    Prev
    Next
    INDEX
    Explanations

    help with

    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
    æݧ
    -0.10
    åŀĵ
    -0.09
     spont
    -0.09
    çĶŁæĢģä¿ĿæĬ¤
    -0.09
    æľºä¼ļ
    -0.09
    æĦıå¤ĸ
    -0.09
    çĬĢ
    -0.08
    è´¯
    -0.08
    åŃļ
    -0.08
     ga
    -0.08
    POSITIVE LOGITS
    å°½åı¯èĥ½
    0.12
    驼
    0.08
    åĨ¶éĩij
    0.08
    åĩŃåĢŁ
    0.08
    ngine
    0.08
    åĩŃåĢŁçĿĢ
    0.08
    åĶ¿
    0.08
    adam
    0.08
    é¦Ĩ
    0.08
    èĻŀ
    0.08
    Activations Density 0.005%

    No Known Activations