© 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. 32581
    Prev
    Next
    INDEX
    Explanations

    he/He followed by verbs

    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
    çĶ¨æ°´
    -0.09
    æīĵæĭ¼
    -0.09
    è§ħ
    -0.09
    çĶļä¹Ī
    -0.09
    cn
    -0.09
    è¾Ĥ
    -0.09
    åµ´
    -0.09
    æĹłå¥Ī
    -0.08
    溷
    -0.08
    åħ¥çĿ¡
    -0.08
    POSITIVE LOGITS
    ï¼Ī
    0.10
    .src
    0.09
    achs
    0.09
    欲
    0.09
    ãĥĹ
    0.09
    æ±Ģ
    0.09
     Viv
    0.08
     [
    0.08
    øj
    0.08
    _generation
    0.08
    Activations Density 0.040%

    No Known Activations