© 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. 53417
    Prev
    Next
    INDEX
    Explanations

    adjective used to describe suitability

    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
     Stevenson
    -0.09
    å¿ĥä¸ŃçļĦ
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    éĶ¦ç»£
    -0.08
    ani
    -0.08
    è¯ļæĦı
    -0.08
    çĶŁæ°Ķ
    -0.08
    idian
    -0.08
    åľ¨æĦı
    -0.08
    usty
    -0.08
    POSITIVE LOGITS
    èĢĮåıĪ
    0.11
    VAS
    0.10
    æī«ä¸Ģæī«
    0.09
    çļĦç¡®
    0.09
    æĢ»è§īå¾Ĺ
    0.09
    è§ģåĪ°
    0.08
    åľ°å¸¦
    0.08
    æīŃæĽ²
    0.08
    讳
    0.08
    TagName
    0.08
    Activations Density 0.562%

    No Known Activations