© 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. 51151
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    etur
    -0.09
    çݯåį«
    -0.08
     sucker
    -0.08
    ä¼Ļ
    -0.08
    adium
    -0.08
     Garr
    -0.08
    åı£æ°Ķ
    -0.08
    Ùĩر
    -0.08
    æµľ
    -0.08
    éĻį
    -0.08
    POSITIVE LOGITS
    幸è¿IJ
    0.10
    çĸı
    0.10
    JECT
    0.09
    èĮķ
    0.09
    é³ľ
    0.09
    ovie
    0.09
    tee
    0.09
    ç´ļ
    0.09
    uby
    0.09
    级
    0.09
    Activations Density 0.057%

    No Known Activations