© 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. 50914
    Prev
    Next
    INDEX
    Explanations

    responsible for publisher

    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
    éĢIJ
    -0.10
     commissioners
    -0.09
    ç»°
    -0.08
    亡
    -0.08
    //------------------------------------------------------------------------------↵
    -0.08
     Mood
    -0.08
    主ä½ĵ
    -0.08
     Buf
    -0.08
    -temp
    -0.08
    å«Į
    -0.08
    POSITIVE LOGITS
    éĨī
    0.11
    itage
    0.10
    被æīĵ
    0.09
    ä¸įæħİ
    0.09
    æŬ
    0.08
    åģı
    0.08
    æĢ§å¼º
    0.08
    åħ¶å®ĥéĹ®é¢ĺ
    0.08
    ä¸įæŃ»
    0.08
    èįĨ
    0.08
    Activations Density 0.001%

    No Known Activations