© 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. 3342
    Prev
    Next
    INDEX
    Explanations

    made of materials

    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
    ç¢ĵ
    -0.08
    ä¸ij
    -0.08
    éľī
    -0.08
    çļĦæĪIJåĬŁ
    -0.08
    çĦĻ
    -0.08
    åĿ¼
    -0.08
    çŤ
    -0.08
    çķĻåѦ
    -0.08
    è§Ħ模
    -0.08
    æ´²
    -0.08
    POSITIVE LOGITS
    æĿIJè´¨
    0.25
    æĿIJæĸĻ
    0.21
     materials
    0.18
     маÑĤеÑĢиалов
    0.16
    materials
    0.16
    è´¨åľ°
    0.16
    æĿIJ
    0.16
     materia
    0.15
     Materials
    0.15
    æĸ°æĿIJæĸĻ
    0.15
    Activations Density 0.249%

    No Known Activations