© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1273
    Prev
    Next
    INDEX
    Explanations

    succulent plants and related botanical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ä¸ĩ欧åħĥ
    -0.24
    bio
    -0.23
    cycl
    -0.22
    çĭłæĬĵ
    -0.22
    bia
    -0.21
    æĺĶ
    -0.21
    积æŀģéħįåIJĪ
    -0.21
    LECTION
    -0.21
    (loop
    -0.21
    eur
    -0.20
    POSITIVE LOGITS
    å½¢çĬ¶
    0.24
    绽
    0.22
    æĮĤ
    0.21
    佬
    0.21
    æł·åŃIJ
    0.21
    ä¸ĬçļĦ
    0.20
    auce
    0.20
    çļ®
    0.20
    éĢłåŀĭ
    0.20
    æ´²
    0.20
    Activations Density 0.002%

    No Known Activations