© 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. 7036
    Prev
    Next
    INDEX
    Explanations

    maturation and maturity

    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
    æĭ
    -0.09
    æĭ¼
    -0.09
    è°Ī
    -0.08
    é«ĺ空
    -0.08
    å«Ĥ
    -0.08
    .ak
    -0.08
    è¡Ķ
    -0.08
    æķĪ
    -0.08
     Resolution
    -0.08
    åĤ
    -0.08
    POSITIVE LOGITS
    æĪIJçĨŁ
    0.35
    æĪIJçĨŁçļĦ
    0.32
     mature
    0.29
     maturity
    0.26
     matures
    0.25
     Mature
    0.23
     immature
    0.17
    æĪIJéķ¿
    0.16
    ç¨ļ
    0.16
     mat
    0.16
    Activations Density 0.123%

    No Known Activations