© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5953
    Prev
    Next
    INDEX
    Explanations

    conjunction introducing a consequence or explanation

    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
     denn
    -0.11
    æŀľçĦ¶
    -0.10
    ãģĿãģĹãģ¦
    -0.10
     ëķĮ문
    -0.10
    æĪij没
    -0.10
    å°¤åħ¶æĺ¯
    -0.09
    åīĶ
    -0.09
    便åı¯
    -0.09
    人éĥ½
    -0.09
    errick
    -0.09
    POSITIVE LOGITS
    ìį¨
    0.11
    -called
    0.09
    å®ŀè´¨
    0.08
    angler
    0.08
    idable
    0.08
    iley
    0.08
     there
    0.08
    typeid
    0.08
    zte
    0.08
    å¤Ħå¤Ħ
    0.08
    Activations Density 0.076%

    No Known Activations