© 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. 26968
    Prev
    Next
    INDEX
    Explanations

    discern, discriminate, distinguish

    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
    åĬ±å¿Ĺ
    -0.09
    æĦ¿æĦı
    -0.09
    æ¿ĢåĬ±
    -0.09
    é¡ĺ
    -0.09
    åįģä¸ĥæĿ¡
    -0.09
    iks
    -0.08
    便æ°ij
    -0.08
    è£ħåį¸
    -0.08
    auer
    -0.08
    襲
    -0.08
    POSITIVE LOGITS
    辨åĪ«
    0.21
    åĪĨ辨
    0.19
    æķıéĶIJ
    0.17
    éī´åĪ«
    0.17
    è¯ĨåĪ«
    0.16
    åĪ¤æĸŃ
    0.16
    åĪ¤
    0.15
    辨
    0.15
    çĶĦ
    0.13
    æĮijåīĶ
    0.13
    Activations Density 0.079%

    No Known Activations