© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9534
    Prev
    Next
    INDEX
    Explanations

    to try and do

    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
    ä¹ĥèĩ³
    -0.10
    è½»æĺĵ
    -0.10
    å°±èĥ½å¤Ł
    -0.09
    å®Įåħ¨åı¯ä»¥
    -0.09
     Carnegie
    -0.09
    çĶļèĩ³
    -0.08
     easily
    -0.08
    bert
    -0.08
    åĿij
    -0.08
    çĶļ
    -0.08
    POSITIVE LOGITS
    åijĹ
    0.14
    åıªèĥ½
    0.13
    å¸ĮæľĽéĢļè¿ĩ
    0.12
    ä¹Łåıªèĥ½
    0.12
    åijĽ
    0.11
    å¸ĮæľĽèĥ½
    0.11
    å°½åĬĽ
    0.11
    åĬĽæ±Ĥ
    0.10
    å¸ĮæľĽèĩªå·±
    0.10
    å°½éĩı
    0.10
    Activations Density 0.035%

    No Known Activations