© 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. 30474
    Prev
    Next
    INDEX
    Explanations

    actor, actress, acting, performances

    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
    imagin
    -0.11
    éĻįèIJ½
    -0.11
    formats
    -0.11
    尾巴
    -0.10
     imagin
    -0.10
    篷
    -0.10
    ORED
    -0.10
    redni
    -0.10
    .CopyTo
    -0.10
     Slayer
    -0.10
    POSITIVE LOGITS
    饰æ¼Ķ
    0.15
    æ¼Ķåijĺ
    0.15
    æ¼ĶæĬĢ
    0.15
    主æ¼Ķ
    0.14
     actor
    0.13
     actors
    0.13
    actor
    0.13
    1
    0.12
    4
    0.12
    0
    0.12
    Activations Density 0.191%

    No Known Activations