© 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. 62120
    Prev
    Next
    INDEX
    Explanations

    "ann" followed by "ine"

    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
    rics
    -0.10
    rac
    -0.10
    æĪŁ
    -0.09
    ject
    -0.09
    磼
    -0.09
    verte
    -0.09
    bron
    -0.09
    bst
    -0.09
    ÂŃs
    -0.09
    æIJł
    -0.09
    POSITIVE LOGITS
    nü
    0.09
    éĢł
    0.09
    erview
    0.09
    å¤ł
    0.08
    äºĽ
    0.08
    ëģĶ
    0.08
     Kad
    0.08
    æĹłçº¿çĶµ
    0.08
    itudes
    0.08
    åĶ®
    0.08
    Activations Density 0.096%

    No Known Activations